Triple

T15909920
Position Surface form Disambiguated ID Type / Status
Subject Elizabeth Miervaldis Lemon E385817 entity
Predicate hasFriend P8712 FINISHED
Object Jack Donaghy E227338 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: Jack Donaghy | Statement: [Elizabeth Miervaldis Lemon, hasFriend, Jack Donaghy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jack Donaghy
Context triple: [Elizabeth Miervaldis Lemon, hasFriend, Jack Donaghy]
  • A. Jack Donaghy chosen
    Jack Donaghy is a sharply dressed, corporate-minded television executive known for his ruthless business savvy and deadpan mentorship of Liz Lemon on the sitcom "30 Rock."
  • B. Rob Mitchell
    Rob Mitchell was a British music executive best known as a co-founder of the influential electronic music label Warp Records.
  • C. David Puddy
    David Puddy is a deadpan, dim-witted auto mechanic and Elaine Benes’s on-again, off-again boyfriend on the sitcom "Seinfeld," known for his monotone delivery and quirky obsessions.
  • D. Peter Sullivan
    Peter Sullivan is a British record producer best known for his work with Tom Jones during the 1960s, helping shape the singer’s early hit sound.
  • E. Peter Sullivan
    Peter Sullivan is the son of Michael Sullivan, a character from the crime drama film "Road to Perdition."
  • 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_69d86da686e4819097cbf3b1fc2d881d completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1565ea7a8819097efffda366b5245 completed April 16, 2026, 9:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb5a5b0dc81909606d667c3bc0edf completed May 9, 2026, 10:31 p.m.
Created at: April 10, 2026, 4:52 a.m.