Triple
T9073962
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Trương Định Ward |
E217439
|
entity |
| Predicate | administrativeUnitLevel |
P87046
|
FINISHED |
| Object | ward-level |
—
|
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: ward-level | Statement: [Trương Định Ward, administrativeUnitLevel, ward-level]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: administrativeUnitLevel Context triple: [Trương Định Ward, administrativeUnitLevel, ward-level]
-
A.
administrativeUnitType
Indicates the specific kind or category of administrative unit involved in the relationship (e.g., city, county, province).
-
B.
isAdministrativeUnit
Indicates that one entity functions as an official administrative division or unit within the governance or organizational structure of another entity.
-
C.
hasAdministrativeUnit
Indicates that one entity possesses, contains, or is associated with another entity that functions as its administrative subdivision or governing unit.
-
D.
laterAdministrativeUnit
Indicates that one administrative unit succeeds or replaces another in time, coming into effect at a later date.
-
E.
topLevelAdministrativeUnitAtTheTime
Indicates the administrative unit that held the highest level of authority over an entity at the specific time in question.
- 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_69ca83d6c14c8190bc056d927f00a2a2 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc956111dc8190a25cefe68fd6a949 |
completed | April 1, 2026, 3:47 a.m. |
| PD | Predicate disambiguation | batch_69cc65fa79bc81908b46f05c8bba920f |
completed | April 1, 2026, 12:25 a.m. |
| PDg | Predicate description generation | batch_69cc6a3c78388190a7436acc0e44ff55 |
completed | April 1, 2026, 12:43 a.m. |
Created at: March 30, 2026, 7:12 p.m.