Triple
T25321512
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anlong Veng |
E634894
|
entity |
| Predicate | lastStrongholdOf |
P89841
|
FINISHED |
| Object | Khmer Rouge |
—
|
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: Khmer Rouge | Statement: [Anlong Veng, lastStrongholdOf, Khmer Rouge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lastStrongholdOf Context triple: [Anlong Veng, lastStrongholdOf, Khmer Rouge]
-
A.
isLastMajorStrongholdOf
chosen
Indicates that a location serves as the final significant defensive or strategic base controlled by a particular entity.
-
B.
strongholdOf
Indicates that a location serves as a primary fortified base, center of power, or main stronghold for a particular entity.
-
C.
primaryStronghold
Indicates that one location serves as the main base, fortress, or central stronghold for an entity compared to its other sites.
-
D.
currentStronghold
Indicates that an entity currently serves as the primary base, fortress, or central stronghold for another entity.
-
E.
wasCitadelOf
Indicates that a place previously served as the main fortified stronghold or central defensive structure for 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_69e75a9847c08190bb02990d06d5ffb7 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f4968e4e70819096256546d76f6e6b |
completed | May 1, 2026, 12:03 p.m. |
| PD | Predicate disambiguation | batch_69f45d06d0388190b36ecde92013624a |
completed | May 1, 2026, 7:57 a.m. |
Created at: April 21, 2026, 1:28 p.m.