Triple

T16895513
Position Surface form Disambiguated ID Type / Status
Subject Wanda Gershwitz E424288 entity
Predicate partnerInCrime P21638 FINISHED
Object George Thomason E418757 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: George Thomason | Statement: [Wanda Gershwitz, partnerInCrime, George Thomason]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George Thomason
Context triple: [Wanda Gershwitz, partnerInCrime, George Thomason]
  • A. George Thomason chosen
    George Thomason is a bumbling British bank robber whose arrest sets off much of the comic chaos in the film "A Fish Called Wanda."
  • B. Andrew Thomason
    Andrew Thomason is a British mathematician renowned for his contributions to combinatorics and graph theory.
  • C. Harry Thomason
    Harry Thomason is an American television producer and director best known for co-creating and producing popular sitcoms such as "Designing Women" and "Evening Shade."
  • D. Jeremy Thomas
    Jeremy Thomas is a Welsh bar owner best known for his brief early-1990s marriage to actress Drew Barrymore.
  • E. Jeremy Thomas
    Jeremy Thomas is a renowned British film producer known for his work on acclaimed independent and art-house films, including multiple collaborations with prominent directors.
  • 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_69d889da3e8c8190a2b118f383f0beac completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e3c8d7aec88190888f13601acbcd77 completed April 18, 2026, 6:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00c7ad473081908b1c1d9524cf64a6 completed May 10, 2026, 6 p.m.
Created at: April 10, 2026, 5:29 a.m.