Triple
T25750296
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lunar Prospector |
E648453
|
entity |
| Predicate | impactedBody |
P163698
|
FINISHED |
| Object | Moon |
—
|
NE NERFINISHED |
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: Moon | Statement: [Lunar Prospector, impactedBody, Moon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: impactedBody Context triple: [Lunar Prospector, impactedBody, Moon]
-
A.
impactingBodyType
Indicates that one entity is characterized by the type or category of body that exerts an impact or collision on another entity.
-
B.
associatedBody
Indicates a relationship where one entity is linked or connected to another entity as its related or corresponding body.
-
C.
intrusiveBodyType
Indicates a relationship where one entity is classified as a type of intrusive body (e.g., geologic or structural feature that has intruded into surrounding material) relative to another.
-
D.
supportingBody
Indicates that one entity serves as a supporting or backing body for another entity, providing endorsement, resources, or structural support.
-
E.
impactedGroup
Indicates the group or population that is affected or influenced by a particular action, event, or condition.
- F. None of above. chosen
Provenance (4 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_69e7ab314d788190b3abe19e114080e1 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6397b64f881909d811225e57aac5e |
completed | May 2, 2026, 5:50 p.m. |
| PD | Predicate disambiguation | batch_69f63706b6008190993577193c85ff50 |
completed | May 2, 2026, 5:40 p.m. |
| PDg | Predicate description generation | batch_69f638d029148190877c103f0eeaf147 |
completed | May 2, 2026, 5:48 p.m. |
Created at: April 22, 2026, 4:33 a.m.