Triple
T31265816
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 21 July 2019 Yuen Long attack |
E797249
|
entity |
| Predicate | injuriesDescription |
P23450
|
FINISHED |
| Object | head wounds and other blunt-force trauma |
—
|
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: head wounds and other blunt-force trauma | Statement: [21 July 2019 Yuen Long attack, injuriesDescription, head wounds and other blunt-force trauma]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: injuriesDescription Context triple: [21 July 2019 Yuen Long attack, injuriesDescription, head wounds and other blunt-force trauma]
-
A.
injuriesApprox
Indicates an approximate or estimated number or extent of injuries associated with an event or entity.
-
B.
injuryType
chosen
Indicates the specific kind or category of injury associated with an entity or event.
-
C.
hasInjuries
Indicates that an entity has sustained one or more physical or bodily injuries.
-
D.
causeOfInjury
Indicates that one entity is the source or reason that another entity sustained an injury.
-
E.
injuredIn
Indicates that an entity sustained an injury as a result of a specified event, situation, or action.
- 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_69f224de2bbc819081af6c32e1d857b9 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69edbb7648190bd89c57e0932eac1 |
completed | May 3, 2026, 1:03 a.m. |
| PD | Predicate disambiguation | batch_69f69d1bf8cc8190a78dfa5ab00daf3a |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 9:12 p.m.