Triple
T26950607
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Du miel aux cendres |
E678766
|
entity |
| Predicate | aimsToExplore |
P1857
|
FINISHED |
| Object | structures of human thought |
—
|
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: structures of human thought | Statement: [Du miel aux cendres, aimsToExplore, structures of human thought]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: aimsToExplore Context triple: [Du miel aux cendres, aimsToExplore, structures of human thought]
-
A.
explores
chosen
Indicates actively investigating, traveling through, or examining something in order to discover or learn more about it.
-
B.
explorationBy
Indicates a relationship where one entity conducts or performs exploration directed at or involving another entity.
-
C.
mayExplore
Indicates that an entity has permission or is allowed to explore another entity, area, or resource.
-
D.
exploresFor
Indicates that one entity actively investigates or searches within or on behalf of another entity, typically to discover or obtain something for that other entity’s benefit.
-
E.
explorationSubject
Indicates that an entity is the focus or target of an exploration, investigation, or exploratory activity carried out by 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_69eeeb4e75f08190b14fc91ca4a91488 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f62089ffe48190b0f7ea25369b1fbf |
completed | May 2, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69f61b3d23f481908dfec27adace900a |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 27, 2026, 6:24 a.m.