Triple
T464270
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peng Dehuai |
E8409
|
entity |
| Predicate | previousOccupation |
P4325
|
FINISHED |
| Object | soldier in the Hunan Army |
—
|
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: soldier in the Hunan Army | Statement: [Peng Dehuai, previousOccupation, soldier in the Hunan Army]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousOccupation Context triple: [Peng Dehuai, previousOccupation, soldier in the Hunan Army]
-
A.
hadOccupationStatusUntil
Indicates that an entity held a particular occupational status up to, but not necessarily beyond, a specified point in time.
-
B.
subjectOccupation
Indicates that the subject holds or performs a particular job, profession, or role as their occupation.
-
C.
parentOccupation
Indicates that one entity has an occupation which is the job or profession of the other entity’s parent.
-
D.
formerEmployer
Indicates that one entity previously employed the other but no longer does so.
-
E.
workedAs
chosen
Indicates that an entity held a particular job, role, or position, performing work in that capacity.
- 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_69a2e7f3aeb48190a19453e3a043f486 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2efd5b6b48190ae23968135cf6417 |
completed | Feb. 28, 2026, 1:38 p.m. |
| PD | Predicate disambiguation | batch_69a2edea1acc81908a72d9f4c43438ea |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.