Triple

T23467859
Position Surface form Disambiguated ID Type / Status
Subject Noelle E569144 entity
Predicate director P255 FINISHED
Object Marc Lawrence 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: Marc Lawrence | Statement: [Noelle, director, Marc Lawrence]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marc Lawrence
Context triple: [Noelle, director, Marc Lawrence]
  • A. Marc Lawrence
    Marc Lawrence was an American character actor best known for his frequent portrayals of gangsters and tough guys in classic Hollywood films.
  • B. Marc Lawrence chosen
    Marc Lawrence is an American screenwriter and film director best known for writing and directing romantic comedies such as "Two Weeks Notice," "Music and Lyrics," and "Miss Congeniality."
  • C. Ben Lawers
    Ben Lawers is one of the highest and most prominent mountains in the Scottish Highlands, renowned for its rich alpine flora and sweeping views over Loch Tay.
  • D. Mark Bignell
    Mark Bignell is a British charity worker and chief executive of the addiction-focused charity Hamoaze House, known publicly as the husband of comedian and actress Dawn French.
  • E. Geoff Lawson
    Geoff Lawson is a former Australian fast bowler and experienced cricket coach who has led various domestic and international teams.
  • 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_69e2458ebd808190b3298163132cfb0b completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a6fd280c81908aae05f0851466eb completed April 29, 2026, 6:36 a.m.
Created at: April 17, 2026, 5:54 p.m.