Triple
T19298400
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zhurong rover |
E482626
|
entity |
| Predicate | radarCapability |
P90739
|
FINISHED |
| Object | Subsurface structure detection |
—
|
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: Subsurface structure detection | Statement: [Zhurong rover, radarCapability, Subsurface structure detection]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: radarCapability Context triple: [Zhurong rover, radarCapability, Subsurface structure detection]
-
A.
radarEquipped
chosen
Indicates that an entity is equipped with or has access to radar detection equipment or radar-based sensing capability.
-
B.
radarEquipment
Indicates that one entity is radar equipment used for detecting, tracking, or measuring objects relative to another entity.
-
C.
radarType
Indicates the specific category or classification of radar associated with an entity.
-
D.
radarRequirement
Indicates that one entity specifies, imposes, or is subject to a requirement related to radar capabilities, performance, or usage in relation to another entity.
-
E.
radarInterface
Indicates that one entity serves as or provides a radar-based interface or interaction layer for another 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_69d8e8cf61b0819096fe3e4107827c4e |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fc86f8648190920d122bb141c6e5 |
completed | April 20, 2026, 10:14 a.m. |
| PD | Predicate disambiguation | batch_69e4dd0bc7508190a6f9d56bd4c3404f |
completed | April 19, 2026, 1:47 p.m. |
Created at: April 10, 2026, 1:31 p.m.