Triple
T37646844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Comanche Peak Unit 2 |
E937059
|
entity |
| Predicate | hasReactorVesselMaterial |
P165114
|
FINISHED |
| Object | low-alloy steel |
—
|
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: low-alloy steel | Statement: [Comanche Peak Unit 2, hasReactorVesselMaterial, low-alloy steel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasReactorVesselMaterial Context triple: [Comanche Peak Unit 2, hasReactorVesselMaterial, low-alloy steel]
-
A.
pressureVesselMaterial
chosen
Indicates that a specified material is used as the construction material for a pressure vessel.
-
B.
vacuumVesselMaterial
Indicates that one entity is the material from which the vacuum vessel of another entity is made.
-
C.
tankMaterial
Indicates that a tank is made of, or primarily constructed from, a specified material.
-
D.
typicalVesselMaterial
Indicates the material that is most commonly or characteristically used to make a given vessel.
-
E.
hasReactorCoolantSystem
Indicates that an entity is equipped with or includes a reactor coolant system used to remove heat from a reactor.
- 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_69f76ed4fe908190b8061c5c135e0971 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1553e08190bb7424c448cb1f33 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:18 p.m.