Triple
T12081829
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lac Pavin |
E287697
|
entity |
| Predicate | hasRiskDiscussion |
P33880
|
FINISHED |
| Object | potential gas release from deep waters |
—
|
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: potential gas release from deep waters | Statement: [Lac Pavin, hasRiskDiscussion, potential gas release from deep waters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRiskDiscussion Context triple: [Lac Pavin, hasRiskDiscussion, potential gas release from deep waters]
-
A.
containsDiscussionOf
chosen
Indicates that one entity includes or features a discussion, treatment, or consideration of another entity as a topic or subject.
-
B.
riskToSpeaker
Indicates that the action, event, or situation poses a potential danger, harm, or adverse consequence to the speaker.
-
C.
hasDiscussionSystem
Indicates that an entity is equipped with or supports a system for facilitating discussions or conversations.
-
D.
hasRiskInFiction
Indicates that a subject is associated with a potential danger, threat, or harmful outcome within a fictional or narrative context.
-
E.
hasWithdrawalRisk
Indicates that discontinuing or reducing something is associated with a risk of withdrawal effects or adverse reactions.
- 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_69d6ab4964708190850585628b287b0c |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9100b4ca8819084845ca4c13e34ce |
completed | April 10, 2026, 2:58 p.m. |
| PD | Predicate disambiguation | batch_69d902bf4f508190842927e7e0642235 |
completed | April 10, 2026, 2:01 p.m. |
Created at: April 8, 2026, 9:48 p.m.