Triple
T23850205
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | شیراز |
E592140
|
entity |
| Predicate | استان |
P604
|
FINISHED |
| Object | استان فارس |
—
|
NE NERFINISHED |
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: استان فارس | Statement: [شیراز, استان, استان فارس]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: استان Context triple: [شیراز, استان, استان فارس]
-
A.
province
chosen
Indicates that one entity is an administrative subdivision or region (a province) governed by or belonging to another, typically larger, political or territorial entity.
-
B.
stateOrRegion
Indicates that one entity is a state or region in which the other entity is located or with which it is associated.
-
C.
countyOrIsland
Indicates that one entity is a county and the other is an island that the county encompasses, is located on, or is otherwise geographically associated with.
-
D.
isProvinceOf
Indicates that one region holds the administrative status of a province within, and is governed as a subnational division of, another political entity.
-
E.
stateOrTerritory
Indicates that one entity is a state or territory that is politically or administratively associated with another entity.
- 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_69e25d221d908190b9b502ad31e66a3f |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c986f7e08190a6d361423946ff05 |
completed | April 29, 2026, 9:04 a.m. |
| PD | Predicate disambiguation | batch_69f1614612b481908c45d99e588882f9 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:11 p.m.