Triple
T7265045
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1996 Manchester bombing |
E159749
|
entity |
| Predicate | estimatedExplosiveMass |
P25889
|
FINISHED |
| Object | 1500 kilograms |
—
|
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: 1500 kilograms | Statement: [1996 Manchester bombing, estimatedExplosiveMass, 1500 kilograms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: estimatedExplosiveMass Context triple: [1996 Manchester bombing, estimatedExplosiveMass, 1500 kilograms]
-
A.
explosiveFillerMass
Indicates the amount of explosive material contained within an object or device.
-
B.
explosiveYieldApprox
chosen
Indicates that one entity has an approximate explosive yield value, typically expressing the estimated magnitude of an explosion or explosive device.
-
C.
estimatedAmmoniumNitrateMass
Indicates the estimated quantity or mass of ammonium nitrate associated with an entity or event.
-
D.
explosiveMaterialUsed
Indicates that an explosive material was employed or involved in carrying out a particular action or event.
-
E.
bombTonnageDropped
Indicates the total weight of bombs that were released or deployed in a given event or 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_69c68838f9948190875fd60b2351230c |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6eb088dac8190b353f6ea3d686025 |
completed | March 27, 2026, 8:39 p.m. |
| PD | Predicate disambiguation | batch_69c6e76876608190ac4652bc7153302e |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 2:57 p.m.