Triple
T20008012
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salva |
E494508
|
entity |
| Predicate | associatedWithHeist |
P132365
|
FINISHED |
| Object | Royal Mint of Spain heist |
—
|
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: Royal Mint of Spain heist | Statement: [Salva, associatedWithHeist, Royal Mint of Spain heist]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithHeist Context triple: [Salva, associatedWithHeist, Royal Mint of Spain heist]
-
A.
associatedWithFictionalGang
Indicates a relationship where an entity is linked or connected to a fictional gang, such as by membership, affiliation, or notable involvement.
-
B.
survivesHeist
Indicates that an entity successfully endures and remains unharmed or intact through the course of a heist.
-
C.
associatedWithGang
Indicates that an entity has a known or alleged connection, membership, or involvement with a gang.
-
D.
partnerInCrime
Indicates a relationship where two or more entities collaborate closely in committing or planning wrongful, illicit, or mischievous acts together.
-
E.
notableHeistType
chosen
Indicates that the subject is notably associated with a specific type or category of heist.
- 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_69da626b2d748190886981ea90c8b2ea |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e661a7500481908b69f74e479f88c8 |
completed | April 20, 2026, 5:25 p.m. |
| PD | Predicate disambiguation | batch_69e54cdddbd48190becc8b2aa5ab4ef9 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 3:33 p.m.