Triple
T28286611
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kalinin-3 |
E713297
|
entity |
| Predicate | usesControlRods |
P103775
|
FINISHED |
| Object | boron-containing control rods |
—
|
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: boron-containing control rods | Statement: [Kalinin-3, usesControlRods, boron-containing control rods]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesControlRods Context triple: [Kalinin-3, usesControlRods, boron-containing control rods]
-
A.
controlRodMaterial
chosen
Indicates the material from which a control rod is made in a nuclear or control system context.
-
B.
controlRodDriveType
Indicates the type or design category of the mechanism used to drive or actuate a control rod.
-
C.
thermalNeutronReactor
Indicates that the subject is a nuclear reactor that operates using thermal (low-energy) neutrons to sustain its fission chain reaction.
-
D.
usesNeutronModerator
Indicates that one entity employs another entity as a neutron moderator to slow down neutrons in a nuclear process or system.
-
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.
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_69efb52371d88190a1381c4e58a3b731 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f6f8565134819096aac0175f924a9f |
completed | May 3, 2026, 7:25 a.m. |
| PD | Predicate disambiguation | batch_69f6f65fd1d08190b88e5e68ba268500 |
completed | May 3, 2026, 7:16 a.m. |
Created at: April 27, 2026, 11:26 p.m.