Triple

T2459460
Position Surface form Disambiguated ID Type / Status
Subject Rollerball E54496 entity
Predicate basedOnAuthor P2806 FINISHED
Object William Harrison E268034 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: William Harrison | Statement: [Rollerball, basedOnAuthor, William Harrison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: William Harrison
Context triple: [Rollerball, basedOnAuthor, William Harrison]
  • A. William Harrison chosen
    William Harrison was an American writer and screenwriter best known for penning the short story and screenplay that inspired the 1975 science fiction film "Rollerball."
  • B. William Henry Harrison
    William Henry Harrison was the ninth president of the United States and a military leader known for his frontier campaigns and brief, 31-day presidency.
  • C. Zachary Taylor
    Zachary Taylor was the 12th president of the United States and a career military officer celebrated as a hero of the Mexican–American War.
  • D. John Tyler
    John Tyler was the 10th president of the United States, known for succeeding William Henry Harrison after his death and for his firm stance on states’ rights.
  • E. Jim Polk
    Jim Polk is an American writer and former spouse of acclaimed Canadian author Margaret Atwood.
  • 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_69ab49dee84c819096b50a0049c347ac completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abd10a35f88190b102a2cb5c88146e completed March 7, 2026, 7:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69af179665d081909f9a761fa50c44e7 completed March 9, 2026, 6:55 p.m.
Created at: March 6, 2026, 9:44 p.m.