Triple

T15291066
Position Surface form Disambiguated ID Type / Status
Subject Eastern Trans-Fly languages E365527 entity
Predicate macroFamilyHypothesis P16671 FINISHED
Object Trans-Fly – Yam family hypothesis
The Trans-Fly – Yam family hypothesis is a proposed higher-level genetic grouping that links the Eastern Trans-Fly languages with the Yam (Morehead–Upper Maro) languages of southern New Guinea into a single language family.
E1147926 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Trans-Fly – Yam family hypothesis | Statement: [Eastern Trans-Fly languages, macroFamilyHypothesis, Trans-Fly – Yam family hypothesis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Trans-Fly – Yam family hypothesis
Context triple: [Eastern Trans-Fly languages, macroFamilyHypothesis, Trans-Fly – Yam family hypothesis]
  • A. Moseten–Chon hypothesis
    The Moseten–Chon hypothesis is a proposed linguistic relationship suggesting that the Mosetenan and Chonan language families of South America may share a common ancestry.
  • B. Hokan hypothesis
    The Hokan hypothesis is a proposed linguistic grouping that suggests several Native American language families of western North America may share a common ancestral origin.
  • C. Austro-Tai hypothesis
    The Austro-Tai hypothesis is a proposed macro-family in historical linguistics that suggests a genetic relationship between the Tai–Kadai languages and the Austronesian language family.
  • D. Sunda-Sulawesi hypothesis
    The Sunda-Sulawesi hypothesis is a proposed subgrouping within the Austronesian language family that suggests a closer genetic relationship among certain languages spoken in western Indonesia and surrounding regions.
  • E. Macro-Tucanoan hypothesis
    The Macro-Tucanoan hypothesis is a proposed large-scale language family grouping that suggests a distant genetic relationship among several indigenous language families of the western Amazon, including Tucanoan and possibly Cahuapanan.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Trans-Fly – Yam family hypothesis
Triple: [Eastern Trans-Fly languages, macroFamilyHypothesis, Trans-Fly – Yam family hypothesis]
Generated description
The Trans-Fly – Yam family hypothesis is a proposed higher-level genetic grouping that links the Eastern Trans-Fly languages with the Yam (Morehead–Upper Maro) languages of southern New Guinea into a single language family.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Trans-Fly – Yam family hypothesis
Target entity description: The Trans-Fly – Yam family hypothesis is a proposed higher-level genetic grouping that links the Eastern Trans-Fly languages with the Yam (Morehead–Upper Maro) languages of southern New Guinea into a single language family.
  • A. Moseten–Chon hypothesis
    The Moseten–Chon hypothesis is a proposed linguistic relationship suggesting that the Mosetenan and Chonan language families of South America may share a common ancestry.
  • B. Hokan hypothesis
    The Hokan hypothesis is a proposed linguistic grouping that suggests several Native American language families of western North America may share a common ancestral origin.
  • C. Austro-Tai hypothesis
    The Austro-Tai hypothesis is a proposed macro-family in historical linguistics that suggests a genetic relationship between the Tai–Kadai languages and the Austronesian language family.
  • D. Sunda-Sulawesi hypothesis
    The Sunda-Sulawesi hypothesis is a proposed subgrouping within the Austronesian language family that suggests a closer genetic relationship among certain languages spoken in western Indonesia and surrounding regions.
  • E. Macro-Tucanoan hypothesis
    The Macro-Tucanoan hypothesis is a proposed large-scale language family grouping that suggests a distant genetic relationship among several indigenous language families of the western Amazon, including Tucanoan and possibly Cahuapanan.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d85a103d9081908c1ea6c4c73ac8e3 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03680b60c8190a3ea54a9d34c8105 completed April 16, 2026, 1:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69feef7d4da4819080f101c3a525ea11 completed May 9, 2026, 8:25 a.m.
NEDg Description generation batch_69fef050d1588190942e1d3f3083607a completed May 9, 2026, 8:29 a.m.
NED2 Entity disambiguation (via description) batch_69fef19d55588190b816d4c37f3a7010 completed May 9, 2026, 8:34 a.m.
Created at: April 10, 2026, 3:15 a.m.