Triple
T17556027
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Surface Warriors |
E427591
|
entity |
| Predicate | refersToPersonnel |
P50783
|
FINISHED |
| Object | soldiers and civilians of SDDC |
—
|
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: soldiers and civilians of SDDC | Statement: [Surface Warriors, refersToPersonnel, soldiers and civilians of SDDC]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: refersToPersonnel Context triple: [Surface Warriors, refersToPersonnel, soldiers and civilians of SDDC]
-
A.
refersToPerson
Indicates that one entity is making reference to, mentioning, or pointing specifically to a particular person.
-
B.
roleInPersonnelMatters
Indicates that one entity has a specific function, authority, or involvement in managing or deciding personnel-related matters concerning another entity.
-
C.
personnel
chosen
Indicates that an entity serves as staff or workforce associated with another entity, such as an organization, project, or facility.
-
D.
refersToPersonFrom
Indicates that one entity makes reference to, mentions, or is about a person originating from or associated with a particular place or group.
-
E.
personnelType
Indicates the classification or role category assigned to a person within an organization or system.
- 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_69d889df6dc081908f67dbadc03c07ee |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4562357b48190bde6f49df0c983c2 |
completed | April 19, 2026, 4:12 a.m. |
| PD | Predicate disambiguation | batch_69e3b4fb39948190a82a597c5bac5c57 |
completed | April 18, 2026, 4:44 p.m. |
Created at: April 10, 2026, 5:50 a.m.