Triple

T6786756
Position Surface form Disambiguated ID Type / Status
Subject Bel languages E155826 entity
Predicate hasMember P10 FINISHED
Object Takia language
The Takia language is an Austronesian language of Papua New Guinea, spoken primarily on Karkar Island and nearby coastal areas of Madang Province.
 E622546 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: Takia language | Statement: [Bel languages, hasMember, Takia language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Takia language
Context triple: [Bel languages, hasMember, Takia language]
  • A. Tigak language
    The Tigak language is an Austronesian language spoken by the Tigak people of New Ireland Province in Papua New Guinea.
  • B. Tanema language
    Tanema is a nearly extinct Oceanic language once spoken on Vanikoro Island in the Temotu Province of the Solomon Islands.
  • C. Mikasuki language
    The Mikasuki language is a Native American Muskogean language traditionally spoken by the Miccosukee and Seminole peoples of Florida.
  • D. Nitinaht language
    The Nitinaht language is a Southern Wakashan Indigenous language spoken by the Ditidaht (Nitinaht) people of Vancouver Island in British Columbia, Canada.
  • E. Towa language
    Towa is a Native American language spoken by the Towa (Jemez) people of New Mexico and is part of the Puebloan language family.
  • 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: Takia language
Triple: [Bel languages, hasMember, Takia language]
Generated description
The Takia language is an Austronesian language of Papua New Guinea, spoken primarily on Karkar Island and nearby coastal areas of Madang Province.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Takia language
Target entity description: The Takia language is an Austronesian language of Papua New Guinea, spoken primarily on Karkar Island and nearby coastal areas of Madang Province.
  • A. Tigak language
    The Tigak language is an Austronesian language spoken by the Tigak people of New Ireland Province in Papua New Guinea.
  • B. Tanema language
    Tanema is a nearly extinct Oceanic language once spoken on Vanikoro Island in the Temotu Province of the Solomon Islands.
  • C. Mikasuki language
    The Mikasuki language is a Native American Muskogean language traditionally spoken by the Miccosukee and Seminole peoples of Florida.
  • D. Nitinaht language
    The Nitinaht language is a Southern Wakashan Indigenous language spoken by the Ditidaht (Nitinaht) people of Vancouver Island in British Columbia, Canada.
  • E. Towa language
    Towa is a Native American language spoken by the Towa (Jemez) people of New Mexico and is part of the Puebloan language family.
  • 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_69c6881770fc8190972b2906390380f5 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d28f043081909a9a9ab635785933 completed March 27, 2026, 6:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69c723cc35cc8190b5affdfd363171ba completed March 28, 2026, 12:41 a.m.
NEDg Description generation batch_69c724e915dc8190a82b69939f78420d completed March 28, 2026, 12:46 a.m.
NED2 Entity disambiguation (via description) batch_69c728ddadd881909c2faa435031a635 completed March 28, 2026, 1:03 a.m.
Created at: March 27, 2026, 2:14 p.m.