Triple
T26955929
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | French Blue |
E678902
|
entity |
| Predicate | estimatedOriginalMass |
P7301
|
FINISHED |
| Object | 67 to 69 carats |
—
|
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: 67 to 69 carats | Statement: [French Blue, estimatedOriginalMass, 67 to 69 carats]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: estimatedOriginalMass Context triple: [French Blue, estimatedOriginalMass, 67 to 69 carats]
-
A.
approximateMass
chosen
Indicates that one entity has a mass value that is an estimate or close approximation of the mass of another entity.
-
B.
estimatedMassInTonnes
Indicates the approximate mass of an entity expressed in metric tonnes.
-
C.
usedTargetMass
Indicates that an action or process utilized a specific mass or quantity of a target entity.
-
D.
systemUsedToDetermineMassOf
Indicates a relationship where a system is employed as the method or tool to measure or calculate the mass of something.
-
E.
estimatedOriginalLength
Indicates the approximated or inferred length that something originally had before any changes, damage, or loss.
- 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_69f64dbbaefc8190952b8320bf4397d8 |
completed | May 2, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_69f64cacd2c08190aed8a1761d0da679 |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 27, 2026, 6:27 a.m.