Triple
T31032234
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unit 4 reactor building |
E790757
|
entity |
| Predicate | causeOfHydrogenExplosion |
P90379
|
FINISHED |
| Object | hydrogen accumulation in upper part of building |
—
|
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: hydrogen accumulation in upper part of building | Statement: [Unit 4 reactor building, causeOfHydrogenExplosion, hydrogen accumulation in upper part of building]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: causeOfHydrogenExplosion Context triple: [Unit 4 reactor building, causeOfHydrogenExplosion, hydrogen accumulation in upper part of building]
-
A.
hydrogenExplosionsOccurredIn
Indicates that one or more hydrogen explosions took place at the specified location or within the specified context.
-
B.
hydrogenExplosionSource
chosen
Indicates that one entity is the origin or cause of a hydrogen explosion affecting another entity.
-
C.
hydrogenExplosionDate
Indicates the date on which a hydrogen explosion occurred or is scheduled to occur.
-
D.
explosionMechanism
Indicates the specific process or mechanism by which an explosion is initiated or occurs.
-
E.
consequenceOfExplosion
Indicates that something occurs as a direct result or outcome of an explosion.
- 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_69f224c97a788190b5da1ead6038a74e |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f78c61ed4c8190ad84c918fa9af55a |
completed | May 3, 2026, 5:56 p.m. |
| PD | Predicate disambiguation | batch_69f78b8cb3a881909ebaac1b503988c2 |
completed | May 3, 2026, 5:53 p.m. |
Created at: April 29, 2026, 8:59 p.m.