Triple
T37034468
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Claudia Wells |
E916587
|
entity |
| Predicate | characterRelationshipPortrayed |
P174335
|
FINISHED |
| Object | girlfriend of Marty McFly |
—
|
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: girlfriend of Marty McFly | Statement: [Claudia Wells, characterRelationshipPortrayed, girlfriend of Marty McFly]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterRelationshipPortrayed Context triple: [Claudia Wells, characterRelationshipPortrayed, girlfriend of Marty McFly]
-
A.
portraysCharacterRelationship
Indicates that one entity depicts or represents the relationship between characters in another entity.
-
B.
portraysRelationship
Indicates that one entity depicts, represents, or illustrates a relationship between other entities.
-
C.
characterActorRelationship
Indicates a relationship where an actor portrays or is associated with a specific character in a work.
-
D.
portraysRelationshipWith
chosen
Indicates that one entity depicts, represents, or characterizes another entity as being in a specific kind of relationship with it or with a third party.
-
E.
characterPortrayedIs
Indicates that one entity serves as the fictional or dramatic role that is depicted or played by another entity.
- 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_69f76e92c7648190bcfa277f64c71a21 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ffc605b0648190a7abe9128b0d857a |
completed | May 9, 2026, 11:40 p.m. |
| PD | Predicate disambiguation | batch_69ffc5742d80819099f947ece78d5700 |
completed | May 9, 2026, 11:38 p.m. |
Created at: May 3, 2026, 4:14 p.m.