Triple
T29756632
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jack Berger |
E753045
|
entity |
| Predicate | relationshipStatusWithCarrieBradshaw |
P154902
|
FINISHED |
| Object | ex-boyfriend |
—
|
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: ex-boyfriend | Statement: [Jack Berger, relationshipStatusWithCarrieBradshaw, ex-boyfriend]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipStatusWithCarrieBradshaw Context triple: [Jack Berger, relationshipStatusWithCarrieBradshaw, ex-boyfriend]
-
A.
relationshipStatusWithCarrie
chosen
Indicates the current nature or state of an entity’s relationship with Carrie.
-
B.
relationshipWithMarieBarone
Indicates that one entity has a specified interpersonal relationship with the person Marie Barone.
-
C.
relationshipStatusWithMichael
Indicates the type or state of the relationship that an entity currently has with Michael.
-
D.
relationshipDynamicWithStaceyColbert
Indicates a changing or evolving interpersonal relationship involving Stacey Colbert.
-
E.
relationshipStatusWithJohnnyGalecki
Indicates the nature or state of a person’s relationship with Johnny Galecki.
- F. None of above.
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_69f0d62c84cc8190846f80ae04fdf8ec |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a01b130f6808190b86442fb16930e6e |
completed | May 11, 2026, 10:36 a.m. |
| PD | Predicate disambiguation | batch_6a01b023157881909a802e06eced3e2f |
completed | May 11, 2026, 10:32 a.m. |
Created at: April 28, 2026, 7:57 p.m.