Triple
T31346567
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fukushima Daiichi Unit 1 |
E799461
|
entity |
| Predicate | fuelRemovalStatus |
P171260
|
FINISHED |
| Object | fuel removed from spent fuel pool |
—
|
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: fuel removed from spent fuel pool | Statement: [Fukushima Daiichi Unit 1, fuelRemovalStatus, fuel removed from spent fuel pool]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fuelRemovalStatus Context triple: [Fukushima Daiichi Unit 1, fuelRemovalStatus, fuel removed from spent fuel pool]
-
A.
fuelCondition
Indicates the state or quality of fuel associated with an entity, such as its level, usability, or readiness for operation.
-
B.
fuelLocation
Indicates the place or source where fuel is stored, supplied, or located for use.
-
C.
hasFuel
Indicates that an entity possesses or contains fuel available for use.
-
D.
fuelTransferMethod
Indicates the method or process by which fuel is transferred from one entity or system to another.
-
E.
hasNoFuelOnSite
Indicates that the specified location or facility does not have any fuel stored or available on its premises.
- F. None of above. chosen
Provenance (4 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_69f224e51614819083141459a080e97c |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69f18afd48190bbbd54e517946499 |
completed | May 3, 2026, 1:04 a.m. |
| PD | Predicate disambiguation | batch_69f69d1d25e88190a7f57d323574da90 |
completed | May 3, 2026, 12:55 a.m. |
| PDg | Predicate description generation | batch_69f69ea761848190acb31298e65b7892 |
completed | May 3, 2026, 1:02 a.m. |
Created at: April 29, 2026, 9:17 p.m.