Triple
T4624013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Halifax Explosion |
E101051
|
entity |
| Predicate | fire |
P52514
|
FINISHED |
| Object | ignited fires throughout north-end Halifax |
—
|
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: ignited fires throughout north-end Halifax | Statement: [Halifax Explosion, fire, ignited fires throughout north-end Halifax]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fire Context triple: [Halifax Explosion, fire, ignited fires throughout north-end Halifax]
-
A.
fires
Indicates that an agent initiates the discharge or ignition of something, such as a weapon, engine, or explosive device, causing it to operate or go off.
-
B.
fireEffect
chosen
Indicates that one entity produces, causes, or is associated with a fire-related impact or consequence on another entity.
-
C.
underFire
Indicates that an entity is being attacked, heavily criticized, or subjected to intense pressure by another entity or group.
-
D.
fireBeganAt
Indicates that the event of a fire starting occurred at a specific time or location.
-
E.
notableFire
Indicates that a significant or historically important fire event is associated with the subject.
- 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_69bd43d0497c8190ac23c65c5804846a |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd5a06d6248190a613be9784dd1ef4 |
completed | March 20, 2026, 2:30 p.m. |
| PD | Predicate disambiguation | batch_69bd5231db7c8190b38d4fdbad8bf842 |
completed | March 20, 2026, 1:57 p.m. |
Created at: March 20, 2026, 1:13 p.m.