Triple
T26263464
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cullinan diamond |
E656914
|
entity |
| Predicate | yieldedFragmentsCount |
P20105
|
FINISHED |
| Object | 9 large stones and 96 smaller brilliants |
—
|
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: 9 large stones and 96 smaller brilliants | Statement: [Cullinan diamond, yieldedFragmentsCount, 9 large stones and 96 smaller brilliants]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: yieldedFragmentsCount Context triple: [Cullinan diamond, yieldedFragmentsCount, 9 large stones and 96 smaller brilliants]
-
A.
numberOfFragmentsApprox
chosen
Indicates an approximate count of how many fragments or pieces are associated with the subject.
-
B.
hasFragments
Indicates that an entity is composed of, contains, or is associated with one or more smaller constituent parts or pieces.
-
C.
numberOfCompletedParts
Indicates the count of parts within a whole that have been finished or fully completed.
-
D.
receiveFiberCount
Indicates that an entity obtains or is assigned a specific number of fiber units from another source or process.
-
E.
hasYield
Indicates that one entity produces, returns, or generates a measurable output, result, or profit for another entity or context.
- 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_69ee5b4e21bc819082be98bc9ab09796 |
completed | April 26, 2026, 6:37 p.m. |
| NER | Named-entity recognition | batch_69f63fd6c68481908c542aa03e297b9c |
completed | May 2, 2026, 6:17 p.m. |
| PD | Predicate disambiguation | batch_69f63c6456608190b94e7c2e2c2a4824 |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 26, 2026, 9:10 p.m.