Triple
T4885821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tianwen-1 |
E109435
|
entity |
| Predicate | scientificInstrumentsOnRover |
P37024
|
FINISHED |
| Object | navigation and terrain camera |
—
|
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: navigation and terrain camera | Statement: [Tianwen-1, scientificInstrumentsOnRover, navigation and terrain camera]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scientificInstrumentsOnRover Context triple: [Tianwen-1, scientificInstrumentsOnRover, navigation and terrain camera]
-
A.
instrumentsOnLander
Indicates that specific instruments are physically mounted on, attached to, or carried by a lander.
-
B.
instrumentsOnOrbiter
Indicates that certain scientific instruments are mounted on and operate from an orbiting spacecraft.
-
C.
roverName
Indicates that an entity is the name assigned to a particular rover.
-
D.
spacecraftComponents
chosen
Indicates that one entity is a spacecraft and the other is a component or part that belongs to or is used in that spacecraft.
-
E.
usedLunarRovingVehicle
Indicates that an entity operated or traveled using a lunar roving vehicle during a lunar mission or activity.
- 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_69bd440f71348190b99938e59fb7f9a1 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6e01872c81909607010c10538ad1 |
completed | March 20, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69bd6c2be5e881909f6ec9c3bcde49f3 |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:28 p.m.