Triple

T12588584
Position Surface form Disambiguated ID Type / Status
Subject Ruth Arnon E300536 entity
Predicate collaboratedWith P435 FINISHED
Object Michael Sela E997425 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: Michael Sela | Statement: [Ruth Arnon, collaboratedWith, Michael Sela]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Sela
Context triple: [Ruth Arnon, collaboratedWith, Michael Sela]
  • A. Michael Sela chosen
    Michael Sela was an Israeli immunologist renowned for his pioneering work on synthetic antigens and for helping develop the multiple sclerosis drug Copaxone.
  • B. Josh Abraham
    Josh Abraham is an American record producer known for his work with prominent rock and alternative bands such as Linkin Park, Limp Bizkit, and Velvet Revolver.
  • C. Tal Berkovich
    Tal Berkovich is an Israeli model and actress known for her work in fashion campaigns and appearances in film and television.
  • D. Osnat Shurer
    Osnat Shurer is an Israeli-American film producer best known for her work on major Walt Disney Animation Studios features such as "Moana" and "Raya and the Last Dragon."
  • E. Tamir Greenwood
    Tamir Greenwood is a child of Radiohead guitarist and composer Jonny Greenwood.
  • 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_69d7bde87b648190bcd0266e9efde098 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d954bd5e8c8190a2f233b91682341f completed April 10, 2026, 7:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69f67c6ddfdc81908df8baa701ed1fbf completed May 2, 2026, 10:36 p.m.
Created at: April 9, 2026, 5:06 p.m.