Triple
T9560165
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Three Mile Island Unit 2 |
E230650
|
entity |
| Predicate | partialMeltdownOccurred |
P89789
|
FINISHED |
| Object | March 28, 1979 |
—
|
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: March 28, 1979 | Statement: [Three Mile Island Unit 2, partialMeltdownOccurred, March 28, 1979]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partialMeltdownOccurred Context triple: [Three Mile Island Unit 2, partialMeltdownOccurred, March 28, 1979]
-
A.
notableInfrastructureFailure
Indicates that a significant piece of infrastructure has failed or malfunctioned in a way that disrupts its normal operation or intended service.
-
B.
hasCrack
Indicates that one entity possesses or exhibits a crack, fracture, or split in its structure or surface.
-
C.
specificationLeakedIn
Indicates that the details or specifications of something have been disclosed or exposed within a particular context, location, or medium without proper authorization.
-
D.
hasMeltingMechanism
Indicates that an entity possesses a specific mechanism or process by which it melts or causes melting.
-
E.
crashResultedIn
Indicates that a crash event caused or led to a particular outcome, consequence, or result.
- 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_69ca847e53a88190a60eed7e02257f10 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd994bde0c8190afcba5cb8fa8b984 |
completed | April 1, 2026, 10:16 p.m. |
| PD | Predicate disambiguation | batch_69ccd594d0ac8190a81bc11a3a538167 |
completed | April 1, 2026, 8:21 a.m. |
| PDg | Predicate description generation | batch_69ccd93e90048190a2b0d7c5c195ba98 |
completed | April 1, 2026, 8:37 a.m. |
Created at: March 30, 2026, 8:03 p.m.