Triple
T37665963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Luncheon Kingdom |
E937819
|
entity |
| Predicate | regionalCoinsShape |
P202317
|
FINISHED |
| Object | triangular purple tomatoes |
—
|
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: triangular purple tomatoes | Statement: [Luncheon Kingdom, regionalCoinsShape, triangular purple tomatoes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regionalCoinsShape Context triple: [Luncheon Kingdom, regionalCoinsShape, triangular purple tomatoes]
-
A.
regionalCoinShape
chosen
Indicates that the coin has a shape characteristic of or specific to a particular geographic region.
-
B.
regionShaped
Indicates that one region determines or influences the shape or form of another region.
-
C.
coinageType
Indicates the specific type or category of coinage associated with an entity, such as its denomination, series, or monetary classification.
-
D.
coinedDesign
Indicates that an entity originated or created a particular design or stylistic concept.
-
E.
hasCantonShape
Indicates that an entity possesses a canton with a specific geometric shape as part of its design or structure.
- 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_69f76ed6df7c8190b018e5baea716ceb |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a007241df8081909dbad651fda82aa7 |
completed | May 10, 2026, 11:55 a.m. |
| PD | Predicate disambiguation | batch_6a0071e77ed081908cd618da8977d878 |
completed | May 10, 2026, 11:54 a.m. |
Created at: May 3, 2026, 4:18 p.m.