Triple
T28421038
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Demon core |
E719940
|
entity |
| Predicate | criticalityAccident |
P165445
|
FINISHED |
| Object | Harry Daghlian accident |
—
|
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: Harry Daghlian accident | Statement: [Demon core, criticalityAccident, Harry Daghlian accident]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: criticalityAccident Context triple: [Demon core, criticalityAccident, Harry Daghlian accident]
-
A.
criticality
Indicates the degree of importance, urgency, or potential impact associated with an entity, condition, or situation within a given context.
-
B.
reactorInvolvedInAccident
Indicates that a specific reactor participated in, contributed to, or was directly affected by a particular accident event.
-
C.
numberOfFuelAssembliesInSpentFuelPoolAtAccident
Indicates the quantity of fuel assemblies that were present in the spent fuel pool at the time of the accident.
-
D.
oneOfWorstNuclearAccidentsWith
Indicates that the subject is associated with another entity as being among the worst nuclear accidents together with it.
-
E.
fuelInReactorCoreAtTimeOfAccident
Indicates that a specified amount or type of fuel was present in the reactor core at the time the accident occurred.
- 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_69eff6f1c5088190bc24bfbf92f9c017 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f659355a208190be2609ffc7a9c427 |
completed | May 2, 2026, 8:06 p.m. |
| PD | Predicate disambiguation | batch_69f6575d89788190aca478e4aea05a65 |
completed | May 2, 2026, 7:58 p.m. |
| PDg | Predicate description generation | batch_69f65875030881909007c502b7dcc998 |
completed | May 2, 2026, 8:03 p.m. |
Created at: April 28, 2026, 1:33 a.m.