Triple

T27674413
Position Surface form Disambiguated ID Type / Status
Subject Tianhe E697740 entity
Predicate attitudeControlSystem P21084 FINISHED
Object reaction control thrusters 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: reaction control thrusters | Statement: [Tianhe, attitudeControlSystem, reaction control thrusters]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: attitudeControlSystem
Context triple: [Tianhe, attitudeControlSystem, reaction control thrusters]
  • A. hasAttitudeControl
    Indicates that an entity possesses the capability or system to control and adjust its orientation or attitude in space.
  • B. attitudeControlMethod chosen
    Indicates the technique or mechanism used to control or adjust the orientation or pointing direction of an object (such as a vehicle or device).
  • C. roleInAttitudeControl
    Indicates that an entity has a specific function or responsibility within an attitude control process or system.
  • D. thrustVectorControl
    Indicates the capability to direct or adjust the direction of thrust from a propulsion system to control an object's attitude or trajectory.
  • E. propulsionModule
    Indicates a relationship where an entity functions as, or is equipped with, a module responsible for providing propulsion.
  • 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_69ef590d458c81909583290c3cd0478b completed April 27, 2026, 12:39 p.m.
NER Named-entity recognition batch_69f63532e35881909bfe0a8a315e2efe completed May 2, 2026, 5:32 p.m.
PD Predicate disambiguation batch_69f62c1a92648190835a2c5250d8c758 completed May 2, 2026, 4:53 p.m.
Created at: April 27, 2026, 2:43 p.m.