Triple

T16073164
Position Surface form Disambiguated ID Type / Status
Subject Samantha Harris E389914 entity
Predicate workedOn P3 FINISHED
Object The Insider E390525 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 Insider | Statement: [Samantha Harris, workedOn, The Insider]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Insider
Context triple: [Samantha Harris, workedOn, The Insider]
  • A. The Insider chosen
    The Insider was an American syndicated entertainment news television program that focused on celebrity news, gossip, and pop culture.
  • B. The Insider (film)
    The Insider is a 1999 drama film directed by Michael Mann that dramatizes tobacco industry whistleblower Jeffrey Wigand’s revelations and their broadcast on CBS’s 60 Minutes.
  • C. Insider
    Insider is a song featured on the Tom Petty and the Heartbreakers album "Hard Promises."
  • D. The Insiders
    The Insiders is the original name of the American soul and R&B group later known as The Main Ingredient.
  • E. The Informant!
    The Informant! is a 2009 dark comedy crime film directed by Steven Soderbergh, in which Matt Damon plays a corporate executive turned whistleblower in a real-life price-fixing scandal.
  • 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_69d86daf32ec8190a8c0466c8f49c3c0 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e183c0390c8190b0da263cccec14e5 completed April 17, 2026, 12:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffe484cef08190a3797c91a7025081 completed May 10, 2026, 1:51 a.m.
Created at: April 10, 2026, 4:57 a.m.