Triple

T14277992
Position Surface form Disambiguated ID Type / Status
Subject Roger Aaron Brown E353962 entity
Predicate notableWork P4 FINISHED
Object The Rock E318018 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: The Rock | Statement: [Roger Aaron Brown, notableWork, The Rock]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Rock
Context triple: [Roger Aaron Brown, notableWork, The Rock]
  • A. The Rock
    The Rock is the nickname of Corregidor, a heavily fortified island in the Philippines that played a crucial role in World War II as a last stronghold of Allied forces in the defense of Manila Bay.
  • B. The Rock chosen
    The Rock is a hugely popular professional wrestler-turned-actor, best known for his charismatic WWE persona and leading roles in major Hollywood action films.
  • C. The Rock
    The Rock is a large, frequently repainted boulder on the Indiana University Bloomington campus that serves as an informal public message board and campus landmark.
  • D. The Rock
    The Rock is a small rural town in New South Wales, Australia, known for the prominent nearby rock formation called The Rock Hill.
  • E. Action Jackson
    Action Jackson is a 1988 American action-comedy film starring Carl Weathers as a tough Detroit police detective battling a corrupt auto tycoon.
  • 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_69d8278d25148190abf1a8c8f5f533ad completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6585270c8190a717127b2f5dab3b completed April 14, 2026, 4:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd326f62b4819084b1e984678991ae completed May 8, 2026, 12:46 a.m.
Created at: April 10, 2026, 1:10 a.m.