Triple
T8448581
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cabanatuan POW camp |
E199742
|
entity |
| Predicate | primaryCampFor |
P55012
|
FINISHED |
| Object | survivors of the Bataan Death March |
—
|
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: survivors of the Bataan Death March | Statement: [Cabanatuan POW camp, primaryCampFor, survivors of the Bataan Death March]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryCampFor Context triple: [Cabanatuan POW camp, primaryCampFor, survivors of the Bataan Death March]
-
A.
primaryProgram
Indicates that one entity serves as the main or principal program associated with another entity, distinguishing it from any secondary or auxiliary programs.
-
B.
primaryServes
Indicates that one entity’s main or principal function is to serve, support, or provide service to another entity.
-
C.
primaryArea
Indicates that one entity is the main or most important area, domain, or field associated with another entity.
-
D.
primaryClass
Indicates that one entity is the main or principal classification category to which another entity belongs.
-
E.
primaryFor
chosen
Indicates that one entity serves as the main or principal option, resource, or association for another entity among possible alternatives.
- 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_69ca83170f9081909cd98f55614c6476 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe445b7988190b53ae45070c70d1d |
completed | March 31, 2026, 3:12 p.m. |
| PD | Predicate disambiguation | batch_69cbd0f5a3648190beb53a139a2d5482 |
completed | March 31, 2026, 1:49 p.m. |
Created at: March 30, 2026, 6:09 p.m.