Triple

T20598563
Position Surface form Disambiguated ID Type / Status
Subject The Jungle Book (1967 film) E506112 entity
Predicate featuresCharacter P626 FINISHED
Object Colonel Hathi 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: Colonel Hathi | Statement: [The Jungle Book (1967 film), featuresCharacter, Colonel Hathi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Colonel Hathi
Context triple: [The Jungle Book (1967 film), featuresCharacter, Colonel Hathi]
  • A. Colonel Hathi chosen
    Colonel Hathi is a pompous but well-meaning elephant military leader from Disney’s animated film "The Jungle Book."
  • B. Colonel Rol
    Colonel Rol was the nom de guerre of French Resistance leader Henri Rol-Tanguy, who played a key role in the liberation of Paris during World War II.
  • C. Colonel Haki
    Colonel Haki is a shrewd and persistent Turkish police officer who aids in unraveling the criminal mystery at the heart of Eric Ambler’s novel "The Mask of Dimitrios."
  • D. Colonel Bob
    Colonel Bob is a prominent peak in Washington State’s Olympic Peninsula, known for its rugged wilderness setting and panoramic views.
  • E. Colonel Howard
    Colonel Howard is a fictional military officer character featured in the film "The Pilot."
  • 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_69e0b4ba6ae88190af871e1f9522c704 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6aa1e251c8190926dafe1402eb63c completed April 20, 2026, 10:35 p.m.
Created at: April 16, 2026, 11:40 a.m.