Triple

T23232639
Position Surface form Disambiguated ID Type / Status
Subject Joan Blackman E581201 entity
Predicate coStarredWith P14987 FINISHED
Object Guy Williams 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: Guy Williams | Statement: [Joan Blackman, coStarredWith, Guy Williams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Guy Williams
Context triple: [Joan Blackman, coStarredWith, Guy Williams]
  • A. Guy Williams chosen
    Guy Williams was an American actor best known for his starring roles in the television series "Zorro" and the science-fiction show "Lost in Space."
  • B. Alexis Denisof
    Alexis Denisof is an American actor best known for his role as Wesley Wyndam-Pryce in the television series "Buffy the Vampire Slayer" and its spin-off "Angel."
  • C. Josh Dallas
    Josh Dallas is an American actor best known for his roles as Prince Charming/David Nolan on the TV series "Once Upon a Time" and as Ben Stone on "Manifest."
  • D. Michael Shanks
    Michael Shanks is a Canadian actor best known for his role as Dr. Daniel Jackson on the science fiction television series Stargate SG-1.
  • E. Luke Goss
    Luke Goss is an English actor and former drummer best known for his roles in genre films such as "Blade II" and "Hellboy II: The Golden Army."
  • 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_69e246043c48819089bae72c9a9c306c completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f192e70b2c8190abede6e3cd9344f7 completed April 29, 2026, 5:11 a.m.
Created at: April 17, 2026, 4:09 p.m.