Triple

T18066164
Position Surface form Disambiguated ID Type / Status
Subject Coosan languages E432298 entity
Predicate hasPart P35 FINISHED
Object Miluk NE NERFINISHED

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: Miluk | Statement: [Coosan languages, hasPart, Miluk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Miluk
Context triple: [Coosan languages, hasPart, Miluk]
  • A. Miluk chosen
    Miluk is an extinct Native American language of the Coosan family that was traditionally spoken along the southern Oregon coast.
  • B. Milyan
    Milyan is an extinct Anatolian Indo-European language once spoken in southwestern Asia Minor, known primarily from a small corpus of inscriptions.
  • C. Maliku
    Maliku is a dialect of the Lawangan language spoken by a subgroup of the Lawangan people in Indonesia.
  • D. Maliku
    Maliku is the traditional local name for Minicoy Island, a culturally distinct island in India’s Lakshadweep archipelago known for its unique Mahl-speaking community and seafaring heritage.
  • E. Mille
    Mille is a French surname most notably borne by individuals such as Stéphane Mille.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9070cac81909fa9473fb1c3f1c7 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4cce97ce08190a2f8762ce545e091 completed April 19, 2026, 12:39 p.m.
Created at: April 10, 2026, 10:26 a.m.