Triple
T4551482
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Belfast Blitz |
E110172
|
entity |
| Predicate | bombTonnage |
P17898
|
FINISHED |
| Object | hundreds of tons of high-explosive bombs dropped |
—
|
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: hundreds of tons of high-explosive bombs dropped | Statement: [Belfast Blitz, bombTonnage, hundreds of tons of high-explosive bombs dropped]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bombTonnage Context triple: [Belfast Blitz, bombTonnage, hundreds of tons of high-explosive bombs dropped]
-
A.
bombTonnageDropped
chosen
Indicates the total weight of bombs that were released or deployed in a given event or context.
-
B.
explosiveYieldApprox
Indicates that one entity has an approximate explosive yield value, typically expressing the estimated magnitude of an explosion or explosive device.
-
C.
warheadMass
Indicates the mass or weight of a warhead associated with an entity or system.
-
D.
bombLoad
Indicates the amount or configuration of bombs carried by an entity, typically an aircraft, for a mission or operation.
-
E.
bombingMethod
Indicates the method or technique used to carry out a bombing.
- 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_69bd4412524c8190be5bcc9ddee91848 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd57f7b9748190af29d02fc77b02e0 |
completed | March 20, 2026, 2:21 p.m. |
| PD | Predicate disambiguation | batch_69bd5223423c81908317351b58cff5f5 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:05 p.m.