Triple
T18704099
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leverage team |
E457326
|
entity |
| Predicate | notableHeistType |
P132365
|
FINISHED |
| Object | corporate fraud exposure |
—
|
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: corporate fraud exposure | Statement: [Leverage team, notableHeistType, corporate fraud exposure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableHeistType Context triple: [Leverage team, notableHeistType, corporate fraud exposure]
-
A.
notableHeistTarget
Indicates that an entity is a significant or high-profile target of a heist or major theft.
-
B.
notableTheft
Indicates that an entity is involved in a theft event that is widely recognized or significant in some notable way.
-
C.
survivesHeist
Indicates that an entity successfully endures and remains unharmed or intact through the course of a heist.
-
D.
notableAsset
Indicates that an entity possesses or is associated with an asset that is particularly significant, prominent, or noteworthy in relation to it.
-
E.
notableTypeOf
Indicates that one entity is a particularly prominent, well-known, or exemplary instance or subtype of another entity.
- F. None of above. chosen
Provenance (4 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_69d8d392aad081909fe31aa03e6e97d1 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5671597ac819093dbb53553130f1e |
completed | April 19, 2026, 11:36 p.m. |
| PD | Predicate disambiguation | batch_69e478de85088190ba5f005f1d39f587 |
completed | April 19, 2026, 6:40 a.m. |
| PDg | Predicate description generation | batch_69e484133ee48190a80f1889d79f34c9 |
completed | April 19, 2026, 7:28 a.m. |
Created at: April 10, 2026, 11:49 a.m.