Triple

T11345643
Position Surface form Disambiguated ID Type / Status
Subject Maury Sterling E268704 entity
Predicate characterRole P268 FINISHED
Object Max E467294 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: Max | Statement: [Maury Sterling, characterRole, Max]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Max
Context triple: [Maury Sterling, characterRole, Max]
  • A. Max
    Max is a masculine given name commonly used in German- and English-speaking countries, often as a short form of Maximilian or Maxwell.
  • B. Max
    Max is a subscription-based streaming service owned by Warner Bros. Discovery that offers a wide range of films, series, and original programming.
  • C. Max chosen
    Max is the ruthless and enigmatic CIA operative who serves as the primary villain in the 2010 action film "The Losers."
  • D. Max
    Max is a film for which acclaimed Hungarian cinematographer Lajos Koltai served as director of photography.
  • E. Max
    Max is a hyperactive, psychotic "rabbit-thing" and one half of the freelance police duo from the comedic adventure game series Sam & Max.
  • 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_69d6aacbe18081909e5fadb50082dd96 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7ea1f9574819089760c5b5908f09e completed April 9, 2026, 6:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5437fb1208190892fa6b05c92478e completed April 19, 2026, 9:05 p.m.
Created at: April 8, 2026, 9:33 p.m.