Triple
T15282140
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | flag of the Balearic Islands |
E365294
|
entity |
| Predicate | cantonCharge |
P117944
|
FINISHED |
| Object | white castle |
—
|
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: white castle | Statement: [flag of the Balearic Islands, cantonCharge, white castle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cantonCharge Context triple: [flag of the Balearic Islands, cantonCharge, white castle]
-
A.
canton
Indicates that an entity is administratively located within, belongs to, or is governed as part of a specific canton.
-
B.
centralCharge
Indicates that an entity has a specific central charge value, typically quantifying a key parameter in a conformal or related physical or mathematical theory.
-
C.
cantonRepresents
Indicates that a canton serves as the official representative or governing authority for a given entity (such as a region, population, or institution).
-
D.
cantonTaxPolicy
Indicates the tax regulations or policies that a canton imposes or applies.
-
E.
cantonCode
Indicates the specific administrative canton identifier associated with an entity or location.
- 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_69d85a103d9081908c1ea6c4c73ac8e3 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e00e51f82081909f63d14b589d5587 |
completed | April 15, 2026, 10:16 p.m. |
| PD | Predicate disambiguation | batch_69deca90739081909bd1b797cdb8af2b |
completed | April 14, 2026, 11:15 p.m. |
| PDg | Predicate description generation | batch_69decf2e413481909d9180a8d78d2c17 |
completed | April 14, 2026, 11:35 p.m. |
Created at: April 10, 2026, 3:15 a.m.