Triple

T4780544
Position Surface form Disambiguated ID Type / Status
Subject Supernatural E106153 entity
Predicate hasPart P35 FINISHED
Object The Calling E338782 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: The Calling | Statement: [Supernatural, hasPart, The Calling]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Calling
Context triple: [Supernatural, hasPart, The Calling]
  • A. The Calling chosen
    The Calling is a British television drama in which Susannah Harker plays a central role, showcasing her work in character-driven storytelling.
  • B. Collective Soul
    Collective Soul is an American rock band, best known for their 1990s hits like "Shine" and "The World I Know," that blends post-grunge and alternative rock styles.
  • C. Lifehouse
    Lifehouse is an American rock band best known for their early-2000s hit single "Hanging by a Moment" and their melodic, radio-friendly alternative rock sound.
  • D. Came the Dawn
    "Came the Dawn" is a humorous short story by P. G. Wodehouse featuring his raconteur character Mr Mulliner.
  • E. Blue October
    Blue October is an American alternative rock band known for emotionally charged songs like "Hate Me" and "Into the Ocean."
  • 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_69bd43f3074c8190937e7b0a457fe9f1 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd65aa577c81909ec1b94e47810169 completed March 20, 2026, 3:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69be43d371b081908142e6d66780e0f0 completed March 21, 2026, 7:08 a.m.
Created at: March 20, 2026, 1:21 p.m.