Triple
T13566151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Macau garrison of the PLA |
E324038
|
entity |
| Predicate | serviceNumberEstimate |
P51380
|
FINISHED |
| Object | several hundred personnel |
—
|
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: several hundred personnel | Statement: [Macau garrison of the PLA, serviceNumberEstimate, several hundred personnel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: serviceNumberEstimate Context triple: [Macau garrison of the PLA, serviceNumberEstimate, several hundred personnel]
-
A.
serviceNumberApproximate
chosen
Indicates that one entity’s service number is approximately equal to, but not necessarily exactly the same as, another entity’s service number.
-
B.
serviceNumber
Indicates a unique identifying number assigned to a service, used to reference, track, or distinguish that service from others.
-
C.
serviceNumberOrEquivalent
Indicates that one entity specifies the service number or an equivalent identifying code associated with another entity.
-
D.
serviceNumberStatus
Indicates the current operational or availability state associated with a specific service number.
-
E.
serviceNumberLabel
Indicates that a label or identifier is assigned to denote the service number associated with an 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_69d8076830b48190910a902bae5888e2 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbb00cecd48190a9a2caff3d424817 |
completed | April 12, 2026, 2:45 p.m. |
| PD | Predicate disambiguation | batch_69dbae161a0481909f9d3f40ca4e0ac5 |
completed | April 12, 2026, 2:37 p.m. |
Created at: April 9, 2026, 9:48 p.m.