Triple
T26883789
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tavernier Blue |
E676984
|
entity |
| Predicate | laterRecutAs |
P98341
|
FINISHED |
| Object | French Blue |
—
|
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: French Blue | Statement: [Tavernier Blue, laterRecutAs, French Blue]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterRecutAs Context triple: [Tavernier Blue, laterRecutAs, French Blue]
-
A.
recutIn
chosen
Indicates that an item has been cut again or re-edited into a new version, typically after an initial cutting or editing process.
-
B.
laterModification
Indicates that one entity is a modification or revision that occurs after another in time.
-
C.
laterRewrittenAs
Indicates that an earlier work, version, or expression was subsequently rewritten or replaced by a later one.
-
D.
recutBy
Indicates that an existing cut or editing of something (such as media or material) has been redone or altered by a particular agent.
-
E.
laterRepurposedFor
Indicates that something was originally used for one purpose and subsequently assigned a different, new purpose.
- 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_69eee9bc0c90819085608c8bdc513a57 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f7aa699d68819081ed363931894ab3 |
completed | May 3, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69f7a8cec6d48190bebfa884b2f938c0 |
completed | May 3, 2026, 7:58 p.m. |
Created at: April 27, 2026, 5:41 a.m.