Triple
T11949264
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bradford City stadium fire |
E284385
|
entity |
| Predicate | likelyIgnitionSource |
P96315
|
FINISHED |
| Object | dropped cigarette or match |
—
|
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: dropped cigarette or match | Statement: [Bradford City stadium fire, likelyIgnitionSource, dropped cigarette or match]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: likelyIgnitionSource Context triple: [Bradford City stadium fire, likelyIgnitionSource, dropped cigarette or match]
-
A.
likelySource
chosen
Indicates that one entity is considered the probable origin or cause of another entity or event.
-
B.
isLessFlammableThan
Indicates that one entity has a lower tendency to catch fire or burn than another entity.
-
C.
isCombustible
Indicates that a substance or material is capable of catching fire and burning under certain conditions.
-
D.
canBePutOutBy
Indicates that one entity has the ability or means to extinguish, stop, or neutralize another entity or process.
-
E.
ignitionMethod
Indicates the specific way or mechanism by which something is ignited or set on fire.
- 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_69d6ab2db38c8190b1f0ed6663ef8ada |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d90346825c8190ab4482a1fc8eed56 |
completed | April 10, 2026, 2:03 p.m. |
| PD | Predicate disambiguation | batch_69d8bb3e48e08190b2fee43af4f57323 |
completed | April 10, 2026, 8:56 a.m. |
Created at: April 8, 2026, 9:45 p.m.