Triple

T10457705
Position Surface form Disambiguated ID Type / Status
Subject Adam Sackler E246588 entity
Predicate hasFriend P8712 FINISHED
Object Marnie Michaels E159706 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: Marnie Michaels | Statement: [Adam Sackler, hasFriend, Marnie Michaels]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marnie Michaels
Context triple: [Adam Sackler, hasFriend, Marnie Michaels]
  • A. Marnie Michaels chosen
    Marnie Michaels is a central character on the HBO series "Girls," known for her ambitious, image-conscious personality and complicated friendships and relationships.
  • B. Marnie Rose Cooper
    Marnie Rose Cooper is the daughter of English singer-songwriter and television personality Lily Allen.
  • C. Cheryl Malone
    Cheryl Malone is a notable individual recognized for achievements significant enough to be associated with the Malone surname.
  • D. Meredith Morton
    Meredith Morton is the uptight, career-driven outsider who becomes the emotional center of the holiday ensemble film "The Family Stone."
  • E. Maggie Gilkeson
    Maggie Gilkeson is the determined frontier mother and healer portrayed by Cate Blanchett in the Western thriller film "The Missing."
  • 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_69d381c04fe08190957c26c526a3b05a completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4fe4a56e08190ab56d762d6a91b01 completed April 7, 2026, 12:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69d89fbf3a308190af6b605ce781396a completed April 10, 2026, 6:59 a.m.
Created at: April 6, 2026, 12:18 p.m.