Triple
T19382094
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MER-B |
E484836
|
entity |
| Predicate | foundEvidenceOf |
P3650
|
FINISHED |
| Object | past liquid water on Mars |
—
|
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: past liquid water on Mars | Statement: [MER-B, foundEvidenceOf, past liquid water on Mars]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: foundEvidenceOf Context triple: [MER-B, foundEvidenceOf, past liquid water on Mars]
-
A.
providesEvidenceFor
chosen
Indicates that one entity serves as support, justification, or proof for the validity or truth of another entity.
-
B.
hasMaterialEvidence
Indicates that there exists tangible, physical evidence supporting or associated with a particular entity, event, or claim.
-
C.
hasNoEvidenceOf
Indicates that there is no supporting proof, data, or documentation confirming the existence or occurrence of the referenced condition, event, or relationship.
-
D.
foundAs
Indicates that one entity is discovered, identified, or observed in the role, form, or state represented by another entity.
-
E.
foundWith
Indicates that one entity is discovered, observed, or obtained in the presence or company of 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_69d8e8d460d88190abf0591c5c9d2b0c |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e61a6075a88190aed7afa3b8fd3021 |
completed | April 20, 2026, 12:21 p.m. |
| PD | Predicate disambiguation | batch_69e4fd602f008190aa9bc76ae17e4ce1 |
completed | April 19, 2026, 4:05 p.m. |
Created at: April 10, 2026, 1:35 p.m.