Triple
T35127582
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pierre Sonnerat |
E1014351
|
entity |
| Predicate | hasMentioned |
P197708
|
FINISHED |
| Object | coco de mer |
—
|
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: coco de mer | Statement: [Pierre Sonnerat, hasMentioned, coco de mer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMentioned Context triple: [Pierre Sonnerat, hasMentioned, coco de mer]
-
A.
hasCharacterMentioned
Indicates that one entity includes a reference to or mention of another entity as a character.
-
B.
hasSpokenAbout
Indicates that one entity has verbally expressed, discussed, or mentioned another entity or topic.
-
C.
hasSaidToBe
Indicates that one entity is reported or claimed to be another entity, typically based on statements or assertions rather than direct verification.
-
D.
publiclyMentionedBy
chosen
Indicates that an entity has been named, referenced, or discussed in a public context by another entity.
-
E.
hasPresented
Indicates that one entity has formally given, delivered, or shown something (such as information, a work, or an award) to 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_69f76dd8b6948190aaa32b081816bd94 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69ff27b125948190aced0fe0189fd39a |
completed | May 9, 2026, 12:25 p.m. |
| PD | Predicate disambiguation | batch_69ff26c30a0481909ef6a54ded851e42 |
completed | May 9, 2026, 12:21 p.m. |
Created at: May 3, 2026, 4:02 p.m.