Triple
T31746151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Umballa |
E810274
|
entity |
| Predicate | hadCantonmentHospital |
P139615
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Umballa, hadCantonmentHospital, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadCantonmentHospital Context triple: [Umballa, hadCantonmentHospital, true]
-
A.
hadCantonmentBarracks
Indicates that a location or authority maintained or was equipped with cantonment barracks used to house military personnel.
-
B.
establishedAsCantonmentBy
Indicates that an entity was designated or set up as a cantonment by a specified agent or authority.
-
C.
wasMilitaryHeadquartersOf
Indicates that a place or facility served as the main command center or headquarters for a specific military force or organization.
-
D.
hasMedicalUnit
chosen
Indicates that an entity possesses, includes, or is associated with a medical unit (such as a clinic, department, or medical team) as part of its structure or resources.
-
E.
hasCantonmentBoard
Indicates that an administrative area possesses or is governed by a cantonment board as its local authority.
- 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_69f348e233cc819083b6695f70cd75d8 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6b21e7e088190832a3db585daea1c |
completed | May 3, 2026, 2:25 a.m. |
| PD | Predicate disambiguation | batch_69f6b14faf608190a25b977c0740729c |
completed | May 3, 2026, 2:22 a.m. |
Created at: April 30, 2026, 11:26 p.m.