Triple
T34459708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nandidurga Fort |
E884598
|
entity |
| Predicate | capturedUnderCommandOf |
P178966
|
FINISHED |
| Object | Lord Cornwallis |
—
|
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: Lord Cornwallis | Statement: [Nandidurga Fort, capturedUnderCommandOf, Lord Cornwallis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capturedUnderCommandOf Context triple: [Nandidurga Fort, capturedUnderCommandOf, Lord Cornwallis]
-
A.
capturedCommander
Indicates that one party has taken a military commander from another party into custody or control.
-
B.
commissionedUnderCommandOf
Indicates that an entity was formally authorized or initiated to act while under the authority or direction of a specific commanding entity.
-
C.
commandeeredBy
Indicates that control or possession of something has been forcibly taken over by a particular agent or group.
-
D.
corpsCommandedUnder
Indicates that one military corps was commanded under the authority or control of another specified commander or higher-level unit.
-
E.
commandingOfficerAfterCapture
Indicates that one entity serves as the commanding officer of another entity after that entity has been captured.
- 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_69f349c73a94819094dfcf50d00620b8 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f719cc31ec819099bebcf833b14d76 |
completed | May 3, 2026, 9:47 a.m. |
| PD | Predicate disambiguation | batch_69f71824431081908d9685d2462ea242 |
completed | May 3, 2026, 9:40 a.m. |
| PDg | Predicate description generation | batch_69f719458378819081725f544efb1173 |
completed | May 3, 2026, 9:45 a.m. |
Created at: May 1, 2026, 2 a.m.