Triple
T8348468
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cullinan I |
E196096
|
entity |
| Predicate | originalRoughWeightSource |
P82219
|
FINISHED |
| Object | 3,106 carat Cullinan diamond |
—
|
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: 3,106 carat Cullinan diamond | Statement: [Cullinan I, originalRoughWeightSource, 3,106 carat Cullinan diamond]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalRoughWeightSource Context triple: [Cullinan I, originalRoughWeightSource, 3,106 carat Cullinan diamond]
-
A.
hasSourceMaterial
Indicates that something is derived from, based on, or created using a particular source material.
-
B.
materialSource
Indicates that one entity serves as the origin or provider of the material or substance used by another entity.
-
C.
physicalOrigin
Indicates that one entity is the place or source from which another entity physically originates or comes into existence.
-
D.
originatesAs
Indicates that one entity begins, arises, or comes into existence in the form, state, or role specified by another entity.
-
E.
originalFor
Indicates that one entity serves as the source, basis, or prototype from which another entity is derived, adapted, or created.
- F. None of above. chosen
Provenance (4 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_69ca82edd63c8190b876b8465464c5fa |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb801588e881908ac0a291280ac0f8 |
completed | March 31, 2026, 8:04 a.m. |
| PD | Predicate disambiguation | batch_69cb70c6d0ec8190acf273b0e007b51a |
completed | March 31, 2026, 6:59 a.m. |
| PDg | Predicate description generation | batch_69cb76d823b08190a54fadb50660cda5 |
completed | March 31, 2026, 7:25 a.m. |
Created at: March 30, 2026, 5:58 p.m.