Triple
T31032235
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unit 4 reactor building |
E790757
|
entity |
| Predicate | effectOfExplosion |
P70979
|
FINISHED |
| Object | severe structural damage to upper floors |
—
|
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: severe structural damage to upper floors | Statement: [Unit 4 reactor building, effectOfExplosion, severe structural damage to upper floors]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: effectOfExplosion Context triple: [Unit 4 reactor building, effectOfExplosion, severe structural damage to upper floors]
-
A.
explosionEffect
Indicates that one entity causes or is associated with an explosive event that produces a sudden, forceful effect on its surroundings.
-
B.
consequenceOfExplosion
chosen
Indicates that something occurs as a direct result or outcome of an explosion.
-
C.
explosionType
Indicates the specific kind or category of explosion associated with an event or entity.
-
D.
explosionOccurred
Indicates that an explosion event has taken place at a specific time and/or location.
-
E.
bombDamage
Indicates that one entity has caused damage to another entity through the use or effects of a bomb.
- 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_69f7817daf00819098936402e75ab0a6 |
completed | May 3, 2026, 5:10 p.m. |
| PD | Predicate disambiguation | batch_69f780fc5ed88190b7200ee5a29940af |
completed | May 3, 2026, 5:08 p.m. |
Created at: April 29, 2026, 8:59 p.m.