Triple
T12205764
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NRX reactor accident of 1952 |
E290831
|
entity |
| Predicate | reactorModerator |
P54126
|
FINISHED |
| Object | heavy water |
—
|
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: heavy water | Statement: [NRX reactor accident of 1952, reactorModerator, heavy water]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reactorModerator Context triple: [NRX reactor accident of 1952, reactorModerator, heavy water]
-
A.
moderator
Indicates that one entity serves as a moderator for another entity, overseeing, managing, or facilitating its activities, interactions, or content.
-
B.
reactor
Indicates a relationship where an entity functions as or is associated with a nuclear or chemical reactor system.
-
C.
usesModerator
chosen
Indicates that an entity employs or relies on a moderator to oversee, regulate, or manage its interactions or processes.
-
D.
moderation
Indicates that an entity exercises restraint, balance, or avoidance of extremes in its actions, behavior, or use of resources.
-
E.
reactorType
Indicates the specific kind or category of reactor associated with an entity.
- 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_69d6ab65923081909acfc61b7a612233 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d920e312708190b4aede2e21f5f697 |
completed | April 10, 2026, 4:10 p.m. |
| PD | Predicate disambiguation | batch_69d91c3d669c81908eea7ad61122d275 |
completed | April 10, 2026, 3:50 p.m. |
Created at: April 8, 2026, 9:51 p.m.