Triple

T5517015
Position Surface form Disambiguated ID Type / Status
Subject James Harper E144709 entity
Predicate name P16 FINISHED
Object James Harper E144709 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: James Harper | Statement: [James Harper, name, James Harper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: James Harper
Context triple: [James Harper, name, James Harper]
  • A. James Harper chosen
    James Harper was a 19th-century American publisher and one of the founding figures behind the influential New York publishing house that became Harper & Brothers.
  • B. Christopher Daniel Barnes
    Christopher Daniel Barnes is an American actor best known for voicing Prince Eric in Disney’s "The Little Mermaid" and Peter Parker/Spider-Man in the 1990s animated series.
  • C. Jonathan Adams
    Jonathan Adams is a Welsh architect best known for designing the iconic Wales Millennium Centre in Cardiff.
  • D. Thaddeus Ross
    Thaddeus Ross is a high-ranking U.S. military officer and government official in Marvel Comics and the Marvel Cinematic Universe, known for his relentless pursuit of the Hulk and later involvement in overseeing superhuman activities.
  • E. Ben Urich
    Ben Urich is a seasoned investigative reporter in Marvel Comics, best known for uncovering superhero secrets and exposing corruption in New York City.
  • 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_69c008f77ff88190b0cd50ca207295d1 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c01f5e8ce08190b7f5f2131bebcd4f completed March 22, 2026, 4:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69c027dd848481908052007e89c3f634 completed March 22, 2026, 5:33 p.m.
Created at: March 22, 2026, 3:33 p.m.