Triple
T9112690
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rupert Graves as DI Greg Lestrade |
E218639
|
entity |
| Predicate | primaryRelationshipType |
P10690
|
FINISHED |
| Object | professional collaborator |
—
|
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: professional collaborator | Statement: [Rupert Graves as DI Greg Lestrade, primaryRelationshipType, professional collaborator]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryRelationshipType Context triple: [Rupert Graves as DI Greg Lestrade, primaryRelationshipType, professional collaborator]
-
A.
relationshipType
chosen
Indicates the specific kind of relationship that exists between two or more entities.
-
B.
parentRelationship
Indicates a familial relationship in which one entity is the parent of another entity.
-
C.
basisOfRelationship
Indicates that one entity serves as the foundational reason, cause, or justification for the relationship that exists between two or more entities.
-
D.
primaryReference
Indicates that one entity serves as the main or authoritative source of information or citation for another entity.
-
E.
relationshipFocus
Indicates a relationship where particular attention, priority, or emphasis is placed on the connection 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_69ca83dc94ac8190b9ef42684d36ff39 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca84b0a048190964f560f78e27cce |
completed | April 1, 2026, 5:08 a.m. |
| PD | Predicate disambiguation | batch_69cc65fe5be081909d4470d6317b14a6 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:16 p.m.