Triple

T1866086
Position Surface form Disambiguated ID Type / Status
Subject X-10 graphite reactor E34923 entity
Predicate laterThermalPower P18503 FINISHED
Object 4000 kW 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: 4000 kW | Statement: [X-10 graphite reactor, laterThermalPower, 4000 kW]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: laterThermalPower
Context triple: [X-10 graphite reactor, laterThermalPower, 4000 kW]
  • A. thermalPower chosen
    Indicates the amount of heat energy per unit time that a system, device, or process generates, transfers, or consumes.
  • B. emitsMoreEnergyThanItReceives
    Indicates that the subject releases a greater amount of energy than it takes in from its surroundings or inputs.
  • C. powerplant
    Indicates that an entity functions as a facility or installation where energy sources are converted into usable power, typically electricity.
  • D. powerplantFor
    Indicates that one entity functions as the power plant or primary energy source serving another entity.
  • E. thermalControl
    Indicates a relationship where one entity regulates, adjusts, or maintains the temperature or thermal conditions of another entity or environment.
  • 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_69a88600b2f88190bc09303e68ab517e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abb16c09e48190a345c95eab59fd87 completed March 7, 2026, 5:02 a.m.
PD Predicate disambiguation batch_69abafe02c3c819093a4744b476106ca completed March 7, 2026, 4:56 a.m.
Created at: March 4, 2026, 7:34 p.m.