Triple

T29898119
Position Surface form Disambiguated ID Type / Status
Subject Gerald Lambeau E759332 entity
Predicate relationshipTypeWithSean Maguire P203664 FINISHED
Object former college roommate LITERAL 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: former college roommate | Statement: [Gerald Lambeau, relationshipTypeWithSean Maguire, former college roommate]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWithSean Maguire
Context triple: [Gerald Lambeau, relationshipTypeWithSean Maguire, former college roommate]
  • A. relationshipTypeWithSeanBoswell
    Indicates the specific nature or category of relationship that an entity has with Sean Boswell.
  • B. relationshipTypeWith Sebastian Wilder
    Indicates the specific nature or category of relationship that an entity has with Sebastian Wilder.
  • C. relationshipTypeWithMarnie
    Indicates the specific nature or category of relationship that an entity has with Marnie.
  • D. relationshipTypeWithGingerMcKenna
    Indicates the specific nature or category of relationship an entity has with Ginger McKenna.
  • E. relationshipTypeWithSamMalone
    Indicates the specific nature or category of relationship that an entity has with Sam Malone.
  • F. None of above. chosen

Provenance (4 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_69f2245f1cf88190978c70d1a1d2cb73 completed April 29, 2026, 3:31 p.m.
NER Named-entity recognition batch_6a01c303af6081909c229b2c8e91c680 completed May 11, 2026, 11:52 a.m.
PD Predicate disambiguation batch_6a01c28ebf54819094318c447d8c7943 completed May 11, 2026, 11:50 a.m.
PDg Predicate description generation batch_6a01c302fe4081908ecbff9ae374f80f completed May 11, 2026, 11:52 a.m.
Created at: April 29, 2026, 6:05 p.m.