Triple
T2815872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bloody Sunday (March 7, 1965) |
E54284
|
entity |
| Predicate | useOfForceByAuthorities |
P18305
|
FINISHED |
| Object | tear gas |
—
|
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: tear gas | Statement: [Bloody Sunday (March 7, 1965), useOfForceByAuthorities, tear gas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: useOfForceByAuthorities Context triple: [Bloody Sunday (March 7, 1965), useOfForceByAuthorities, tear gas]
-
A.
authorizedUseOfForce
Indicates that an entity has been granted legitimate permission to apply physical force under specified conditions or authority.
-
B.
militaryForceUsed
Indicates that one entity employs or applies military power or armed force against, within, or in relation to another entity or situation.
-
C.
typeOfLawEnforcement
Indicates that one entity is a specific kind or category of law enforcement associated with another entity.
-
D.
lawEnforcementResponse
chosen
Indicates the actions or measures taken by law enforcement agencies in reaction to an incident, behavior, or situation.
-
E.
exerciseOfPower
Indicates the exertion or application of authority, control, or influence by one entity over another or within a given context.
- 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_69ab49de0af08190b3da69683be1e728 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abde4ed4ac81909f1ec4a3f7869bc1 |
completed | March 7, 2026, 8:14 a.m. |
| PD | Predicate disambiguation | batch_69abdd0740208190911dc9c9546a79ae |
completed | March 7, 2026, 8:08 a.m. |
Created at: March 6, 2026, 9:59 p.m.