Triple
T26718629
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thailand administrative divisions |
E673634
|
entity |
| Predicate | BangkokDistrictsDividedInto |
P50633
|
FINISHED |
| Object | subdistricts (khwaeng) |
—
|
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: subdistricts (khwaeng) | Statement: [Thailand administrative divisions, BangkokDistrictsDividedInto, subdistricts (khwaeng)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: BangkokDistrictsDividedInto Context triple: [Thailand administrative divisions, BangkokDistrictsDividedInto, subdistricts (khwaeng)]
-
A.
subdistrictOf
Indicates that one administrative subdistrict is geographically and politically contained within, and is a part of, a larger district.
-
B.
hasNumberOfSubdistricts
Indicates the relationship specifying how many subdistricts are associated with a given entity.
-
C.
governmentDistrict
Indicates that a government entity has jurisdiction over or is administratively associated with a specific district.
-
D.
subdistrictIn
Indicates that one administrative subdistrict is geographically or jurisdictionally contained within a larger district or region.
-
E.
dividesUrbanAreaInto
chosen
Indicates that one entity partitions or segments an urban area into distinct parts or zones.
- 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_69eecda481d08190aea69f2f7c745f56 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f61fd623bc819091df736cf3419b99 |
completed | May 2, 2026, 4:01 p.m. |
| PD | Predicate disambiguation | batch_69f61b3d23f481908dfec27adace900a |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 27, 2026, 3:39 a.m.