Triple
T10391177
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kingsman headquarters |
E244894
|
entity |
| Predicate | hasCoverIdentity |
P42867
|
FINISHED |
| Object | Savile Row tailor shop |
—
|
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: Savile Row tailor shop | Statement: [Kingsman headquarters, hasCoverIdentity, Savile Row tailor shop]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCoverIdentity Context triple: [Kingsman headquarters, hasCoverIdentity, Savile Row tailor shop]
-
A.
hasSecretIdentity
chosen
Indicates that an entity possesses an alternate, hidden identity that is not publicly known.
-
B.
appearsInIdentity
Indicates that an entity is featured, referenced, or plays a role within a particular identity or identity-related context.
-
C.
hasIdentity
Indicates that one entity is the same as, or is identified as, another specific entity or identifier.
-
D.
hasCoverType
Indicates that one entity possesses or is associated with a specific type or category of cover.
-
E.
hasImaginedIdentity
Indicates that an entity mentally constructs or adopts a non-actual identity, role, or persona for itself or 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_69d381b5116081908d85227bab6d3c0c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e9b5b43081908641a5abfb08dc2b |
completed | April 7, 2026, 11:25 a.m. |
| PD | Predicate disambiguation | batch_69d4dfb0e7a88190bec0b7a52c70dfe2 |
completed | April 7, 2026, 10:42 a.m. |
Created at: April 6, 2026, 12:06 p.m.