Triple

T23300851
Position Surface form Disambiguated ID Type / Status
Subject Miller v Jackson E590297 entity
Predicate parties P1790 FINISHED
Object 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: Jackson | Statement: [Miller v Jackson, parties, Jackson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jackson
Context triple: [Miller v Jackson, parties, Jackson]
  • A. Jackson chosen
    Jackson is a common English surname borne by numerous notable figures across politics, science, sports, and the arts.
  • B. Jackson
    "Jackson" is a classic country duet, famously performed by Johnny Cash and June Carter, about a fiery, deteriorating marriage and the lure of wild living in the town of Jackson.
  • C. Jackson
    Jackson is a city in Michigan that serves as the home of Cascades Falls Park, a popular local landmark known for its illuminated, man-made waterfalls.
  • D. Jackson
    Jackson is the naive but determined protagonist of Chester Himes’s crime novel *A Rage in Harlem*, whose misadventures drive the story’s darkly comic plot.
  • E. Jackson
    Jackson is a fictional crew member aboard the USCSS Prometheus in the science fiction film "Prometheus" from the Alien franchise.
  • 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_69e25d1c0ecc8190a355aa229f06d0e0 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f196d37fd08190ad2d199c54324c02 completed April 29, 2026, 5:27 a.m.
Created at: April 17, 2026, 5:04 p.m.