Triple
T10928786
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bianca Taylor |
E258143
|
entity |
| Predicate | relationshipStatusInCreed |
P10690
|
FINISHED |
| Object | girlfriend of Adonis Creed |
—
|
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 Adonis Creed | Statement: [Bianca Taylor, relationshipStatusInCreed, girlfriend of Adonis Creed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipStatusInCreed Context triple: [Bianca Taylor, relationshipStatusInCreed, girlfriend of Adonis Creed]
-
A.
roleInCreed
Indicates that an entity holds a specific role or function within a particular creed, doctrine, or belief system.
-
B.
relationshipStatusDuringFilm
Indicates the type or state of a relationship between entities specifically during the time period in which a film takes place or is produced.
-
C.
relationToOtherCreeds
Indicates how one belief system, doctrine, or creed is positioned or related in comparison to other creeds.
-
D.
inRelationshipWith
Indicates that two entities are mutually involved in a defined personal, romantic, or partnership relationship with each other.
-
E.
relationshipType
chosen
Indicates the specific kind of relationship that exists between two or more entities.
- 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_69d6aa864ed88190818280ab6791d065 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7709eb0ec819093f7d3f99097bbe4 |
completed | April 9, 2026, 9:25 a.m. |
| PD | Predicate disambiguation | batch_69d72e799f808190b6ab64fc7586a303 |
completed | April 9, 2026, 4:43 a.m. |
Created at: April 8, 2026, 9:22 p.m.