Triple

T20154481
Position Surface form Disambiguated ID Type / Status
Subject Cliff Green E491517 entity
Predicate notableWork P4 FINISHED
Object Marion 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: Marion | Statement: [Cliff Green, notableWork, Marion]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marion
Context triple: [Cliff Green, notableWork, Marion]
  • A. Marion
    Marion is a given name used for people of any gender in various cultures, often as a variant of Mary or Marian.
  • B. Marion
    Marion is a neighborhood or village within the town of Southington, Connecticut, known as one of its local residential communities.
  • C. Marion
    Marion is a small historic city in central Alabama known for its role in the civil rights movement and as the home of several longstanding educational institutions.
  • D. Marion
    Marion is a small town located in Guadalupe County in the U.S. state of Texas.
  • E. Marion
    Marion is a fictional character appearing in the satirical soap-opera sketch series "As the Stomach Turns" from The Carol Burnett Show.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen

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_69da6265f8f0819080b29c752a574088 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e667de9bec8190836887c86dbcf28d completed April 20, 2026, 5:52 p.m.
Created at: April 11, 2026, 11:34 p.m.