Triple

T21086337
Position Surface form Disambiguated ID Type / Status
Subject Javan langur E519498 entity
Predicate commonName P570 FINISHED
Object Javan langur 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: Javan langur | Statement: [Javan langur, commonName, Javan langur]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Javan langur
Context triple: [Javan langur, commonName, Javan langur]
  • A. Javan langur chosen
    The Javan langur is an Old World monkey species endemic to the Indonesian island of Java, known for its arboreal lifestyle and distinctive dark or orange fur.
  • B. Hanuman langur
    The Hanuman langur is a widespread South Asian Old World monkey species known for its long tail, grayish fur, and cultural significance in Hindu mythology.
  • C. Mentawai langur
    The Mentawai langur is a critically endangered primate species of leaf-eating monkey found only on Indonesia’s Mentawai Islands.
  • D. Javan gibbon
    The Javan gibbon is an endangered, arboreal primate endemic to the forests of Java, Indonesia, known for its loud territorial songs and brachiating locomotion through the forest canopy.
  • E. Nilgiri langur
    The Nilgiri langur is a dark-furred, long-tailed Old World monkey endemic to the forests of the Western Ghats in southern India.
  • 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_69e0b507dd9081908fb8bfcbef4c8b46 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7094ad1c08190a4b9d2668a6362b2 completed April 21, 2026, 5:21 a.m.
Created at: April 16, 2026, 2:50 p.m.