Triple
T7295581
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cullinan II |
E164511
|
entity |
| Predicate | rankBySizeFromCullinan |
P1174
|
FINISHED |
| Object | second largest |
—
|
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: second largest | Statement: [Cullinan II, rankBySizeFromCullinan, second largest]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rankBySizeFromCullinan Context triple: [Cullinan II, rankBySizeFromCullinan, second largest]
-
A.
rankBySize
chosen
Indicates that entities are ordered or compared based on their size.
-
B.
positionOfCullinanII
Indicates the current physical location or placement of the Cullinan II diamond.
-
C.
caratWeight
Indicates the weight of a gemstone or diamond, measured in carats, associated with an item or entity.
-
D.
rankByLength
Indicates ordering a set of items based on their length, typically from shortest to longest or vice versa.
-
E.
rankingInCountryBySize
Indicates the position of an entity in an ordered list of entities within a specific country, based on their relative size.
- 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_69c6887a499881909dd23341399c59d8 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6eb8d0c6c8190b32cd08b9a5d96cc |
completed | March 27, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69c6e76c5fbc8190b378830082f11cb0 |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 3 p.m.