Triple

T7103177
Position Surface form Disambiguated ID Type / Status
Subject Sumba people E165509 entity
Predicate language P15 FINISHED
Object Lewa language
Lewa language is an Austronesian language spoken by the Sumba people on Sumba Island in eastern Indonesia.
E642379 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: Lewa language | Statement: [Sumba people, language, Lewa language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lewa language
Context triple: [Sumba people, language, Lewa language]
  • A. Lemolang language
    Lemolang is an Austronesian language spoken by a small community in South Sulawesi, Indonesia.
  • B. Lavukaleve language
    Lavukaleve is a Papuan language spoken by the Lavukal people of the Russell Islands in the Solomon Islands, known for its complex grammar and status as one of the Central Solomons languages.
  • C. Lusei language
    The Lusei language is a Kuki-Chin language of the Tibeto-Burman family spoken primarily by the Lusei (Mizo) people in northeastern India, especially in Mizoram.
  • D. Woleaian language
    The Woleaian language is a Micronesian language spoken primarily on the atolls of Woleai and nearby islands in the Federated States of Micronesia.
  • E. Logba language
    The Logba language is a Niger-Congo language spoken by the Logba people of southeastern Ghana.
  • 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: Lewa language
Triple: [Sumba people, language, Lewa language]
Generated description
Lewa language is an Austronesian language spoken by the Sumba people on Sumba Island in eastern Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lewa language
Target entity description: Lewa language is an Austronesian language spoken by the Sumba people on Sumba Island in eastern Indonesia.
  • A. Lemolang language
    Lemolang is an Austronesian language spoken by a small community in South Sulawesi, Indonesia.
  • B. Lavukaleve language
    Lavukaleve is a Papuan language spoken by the Lavukal people of the Russell Islands in the Solomon Islands, known for its complex grammar and status as one of the Central Solomons languages.
  • C. Lusei language
    The Lusei language is a Kuki-Chin language of the Tibeto-Burman family spoken primarily by the Lusei (Mizo) people in northeastern India, especially in Mizoram.
  • D. Woleaian language
    The Woleaian language is a Micronesian language spoken primarily on the atolls of Woleai and nearby islands in the Federated States of Micronesia.
  • E. Logba language
    The Logba language is a Niger-Congo language spoken by the Logba people of southeastern Ghana.
  • 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_69c6887fcddc8190a5d58908f6dee590 completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e58a0a2c819088e0c8874fb4491f completed March 27, 2026, 8:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69c79cad60788190bb2b17d1c3f8e1cc completed March 28, 2026, 9:17 a.m.
NEDg Description generation batch_69c79d72dd70819084a4bf7e72865ed9 completed March 28, 2026, 9:20 a.m.
NED2 Entity disambiguation (via description) batch_69c79e12a40c8190b21128e17c3e212e completed March 28, 2026, 9:23 a.m.
Created at: March 27, 2026, 2:42 p.m.