Triple

T16744789
Position Surface form Disambiguated ID Type / Status
Subject Louis Tully E406923 entity
Predicate friendOf P8712 FINISHED
Object Ray Stantz E377580 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: Ray Stantz | Statement: [Louis Tully, friendOf, Ray Stantz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ray Stantz
Context triple: [Louis Tully, friendOf, Ray Stantz]
  • A. Ray Stantz chosen
    Ray Stantz is a passionate, good-natured paranormal investigator and founding member of the Ghostbusters team, known for his childlike enthusiasm and deep knowledge of the supernatural.
  • B. Dr. Samuel Loomis
    Dr. Samuel Loomis is a fictional psychiatrist and determined nemesis of the killer Michael Myers in the Halloween horror film franchise.
  • C. Sam Loomis
    Sam Loomis is a central character in Alfred Hitchcock's classic horror film "Psycho," known as Marion Crane's boyfriend who becomes involved in investigating her disappearance.
  • D. Martin Brody
    Martin Brody is the cautious, duty-driven police chief of Amity Island who becomes the central human protagonist battling the great white shark in the film "Jaws."
  • E. Willis Hale
    Willis Hale was an American architect known for his highly ornate and eccentric Victorian-era buildings in Philadelphia.
  • 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_69d8838ffb088190a0b11149929006bf completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3aa210ef88190be74bd60d7144953 completed April 18, 2026, 3:58 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00a51e69c08190a5bff74823df430c completed May 10, 2026, 3:32 p.m.
Created at: April 10, 2026, 5:21 a.m.