Triple

T18809352
Position Surface form Disambiguated ID Type / Status
Subject Thomas Meehan E459965 entity
Predicate coWroteWith P2389 FINISHED
Object Mark O'Donnell 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: Mark O'Donnell | Statement: [Thomas Meehan, coWroteWith, Mark O'Donnell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mark O'Donnell
Context triple: [Thomas Meehan, coWroteWith, Mark O'Donnell]
  • A. Mark O’Donnell chosen
    Mark O’Donnell was an American playwright and humorist best known as the co-writer of the Tony Award–winning musical adaptation of John Waters’ film "Hairspray."
  • B. Jim O’Doherty
    Jim O’Doherty is an American television writer and producer known for creating and working on various youth-oriented comedy series.
  • C. Mark O’Connor
    Mark O’Connor is an American violinist, composer, and fiddler renowned for blending classical, jazz, and American folk traditions, particularly in contemporary string music.
  • D. Mark O’Connor
    Mark O’Connor is a cinematographer known for his work on documentary and feature films, including the 2015 documentary "This Changes Everything."
  • E. Mark O'Rowe
    Mark O'Rowe is an Irish playwright, screenwriter, and director known for his gritty, character-driven works in theatre and film.
  • 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_69d8d398c7d4819091cb2f7e48948aeb completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5a3db38ec8190ab5bef15bc6789be completed April 20, 2026, 3:56 a.m.
Created at: April 10, 2026, 11:53 a.m.