Triple
T26357217
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Special Investigations Unit |
E663096
|
entity |
| Predicate | typeOfIncidentInvestigated |
P16515
|
FINISHED |
| Object | serious injury |
—
|
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: serious injury | Statement: [Special Investigations Unit, typeOfIncidentInvestigated, serious injury]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfIncidentInvestigated Context triple: [Special Investigations Unit, typeOfIncidentInvestigated, serious injury]
-
A.
investigatedEvent
chosen
Indicates that an event was the subject of an investigation or inquiry carried out by some agent.
-
B.
notableIncidentType
Indicates the specific category or kind of significant event or incident associated with an entity.
-
C.
commonIncidentType
Indicates that multiple entities share the same category or type of incident.
-
D.
incidentWith
Indicates that one entity is involved in, affected by, or associated with a particular incident or event together with another entity.
-
E.
typeOfInvestigation
Indicates the specific kind or category of investigation being conducted or referred to in the relationship.
- 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_69ee8130fc44819094e5ab1da201cd7b |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69fcc4b700748190ae00b21d09c96695 |
completed | May 7, 2026, 4:58 p.m. |
| PD | Predicate disambiguation | batch_69fcb0f9d3d881908a049475182fb039 |
completed | May 7, 2026, 3:34 p.m. |
Created at: April 26, 2026, 10:49 p.m.