Triple

T8267693
Position Surface form Disambiguated ID Type / Status
Subject Mark Harmon E193341 entity
Predicate spouse P13 FINISHED
Object Pam Dawber E373010 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: Pam Dawber | Statement: [Mark Harmon, spouse, Pam Dawber]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pam Dawber
Context triple: [Mark Harmon, spouse, Pam Dawber]
  • A. Pam Dawber chosen
    Pam Dawber is an American actress best known for starring opposite Robin Williams in the television sitcom "Mork & Mindy."
  • B. Cindy Williams
    Cindy Williams was an American actress best known for her role as Shirley Feeney on the hit television sitcom "Laverne & Shirley."
  • C. Julie Kavner
    Julie Kavner is an American actress and voice actress best known for voicing Marge Simpson and other characters on the long-running animated television series "The Simpsons."
  • D. Laraine Newman
    Laraine Newman is an American comedian and actress best known as one of the original cast members of Saturday Night Live in the 1970s.
  • E. Mary Lynn Rajskub
    Mary Lynn Rajskub is an American actress and comedian best known for her role as Chloe O'Brian on the television series "24."
  • 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_69ca82e081d48190986beaa51f498ab9 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb794fc4208190b268bc69ff2b28a9 completed March 31, 2026, 7:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd6833065c8190945e88022ad2869d completed April 1, 2026, 6:47 p.m.
Created at: March 30, 2026, 5:50 p.m.