Triple

T14887773
Position Surface form Disambiguated ID Type / Status
Subject Margaery Tyrell E359672 entity
Predicate creator P184 FINISHED
Object George R. R. Martin E68797 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 R. R. Martin | Statement: [Margaery Tyrell, creator, George R. R. Martin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George R. R. Martin
Context triple: [Margaery Tyrell, creator, George R. R. Martin]
  • A. George R. R. Martin chosen
    George R. R. Martin is an American fantasy author best known for his epic series "A Song of Ice and Fire," which was adapted into the television phenomenon "Game of Thrones."
  • B. A. R. Martin
    A. R. Martin is an editor best known for overseeing the influential British Interplanetary Society study volume on the interstellar spacecraft concept Project Daedalus.
  • C. Robert Jordan
    Robert Jordan is a political figure who ran as a candidate in San Francisco’s 2019 mayoral election.
  • D. Robert Jordan
    Robert Jordan is the American dynamiter and Spanish Civil War volunteer who serves as the idealistic yet introspective protagonist of Ernest Hemingway’s novel "For Whom the Bell Tolls."
  • E. Robert Jordan
    Robert Jordan was an American fantasy author best known for creating the epic series "The Wheel of Time."
  • 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_69d827980cbc8190a0c569ae3940a1d9 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69ded5f5b1c88190815f3585770cb135 completed April 15, 2026, 12:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe6b495800819091c7e1636514222a completed May 8, 2026, 11:01 p.m.
Created at: April 10, 2026, 2:08 a.m.