Triple
T15229365
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lochnagar Crater |
E363957
|
entity |
| Predicate | explosiveChargeMassApprox |
P49453
|
FINISHED |
| Object | 27,000 kilograms of ammonal |
—
|
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: 27,000 kilograms of ammonal | Statement: [Lochnagar Crater, explosiveChargeMassApprox, 27,000 kilograms of ammonal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: explosiveChargeMassApprox Context triple: [Lochnagar Crater, explosiveChargeMassApprox, 27,000 kilograms of ammonal]
-
A.
explosiveFillerMass
chosen
Indicates the amount of explosive material contained within an object or device.
-
B.
explosiveMaterialUsed
Indicates that an explosive material was employed or involved in carrying out a particular action or event.
-
C.
estimatedAmmoniumNitrateMass
Indicates the estimated quantity or mass of ammonium nitrate associated with an entity or event.
-
D.
warheadMass
Indicates the mass or weight of a warhead associated with an entity or system.
-
E.
explosiveDevice
Indicates the presence or involvement of an object designed to explode or cause an explosion in relation to the associated entities.
- 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_69d85a0ce24c81909c4d3b6475548c95 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0078ccdf48190b34eabd9e24e45a1 |
completed | April 15, 2026, 9:47 p.m. |
| PD | Predicate disambiguation | batch_69deca899d5c8190be4a7c71e1683c69 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:12 a.m.