Triple

T7103176
Position Surface form Disambiguated ID Type / Status
Subject Sumba people E165509 entity
Predicate language P15 FINISHED
Object Anakalangu language E157756 NE FINISHED

How this triple was built (2 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: Anakalangu language | Statement: [Sumba people, language, Anakalangu language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anakalangu language
Context triple: [Sumba people, language, Anakalangu language]
  • A. Anakalangu language chosen
    The Anakalangu language is an Austronesian language spoken by communities on the island of Sumba in eastern Indonesia.
  • B. Anuak language
    The Anuak language is a Nilotic language spoken primarily by the Anuak people of western Ethiopia and eastern South Sudan.
  • C. Agutaynen language
    Agutaynen is an Austronesian language spoken by the Agutaynen people of Palawan in the Philippines.
  • D. Kalanguya language
    The Kalanguya language is an Austronesian language spoken by the Kalanguya people in the northern Luzon highlands of the Philippines.
  • E. Blablanga language
    The Blablanga language is an Oceanic language spoken in the Solomon Islands, belonging to the Northwest Solomonic subgroup of the Austronesian language family.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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.
Created at: March 27, 2026, 2:42 p.m.