Triple

T23008399
Position Surface form Disambiguated ID Type / Status
Subject John Jackson E572841 entity
Predicate name P16 FINISHED
Object John Jackson 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: John Jackson | Statement: [John Jackson, name, John Jackson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Jackson
Context triple: [John Jackson, name, John Jackson]
  • A. John Jackson chosen
    John Jackson was the father of Julia Prinsep Duckworth, making him the maternal grandfather of the writer Virginia Woolf.
  • B. John Jackson Parr
    John Jackson Parr is the infant son of the superhero Parr family in Pixar's "The Incredibles," known for manifesting a wide array of unpredictable superpowers.
  • C. Jonathan Jackson
    Jonathan Jackson is an American businessman and Democratic politician who serves as a U.S. Representative from Illinois and is the son of civil rights leader Jesse Jackson.
  • D. Jonathan Jackson
    Jonathan Jackson is an American actor and musician best known for his roles on the soap opera "General Hospital" and the television series "Nashville."
  • E. Jonathan Jackson
    Jonathan Jackson was a prominent 18th-century American merchant and politician from Massachusetts who served in the Continental Congress and held several key state and federal offices during and after the American Revolution.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69e245b764cc8190a51be76f1d9611e1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1835919b08190ba78e182b87358d4 completed April 29, 2026, 4:04 a.m.
Created at: April 17, 2026, 3:51 p.m.