Triple
T35897285
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Volunteers |
E1038259
|
entity |
| Predicate | recruitmentChannelFor |
P157499
|
FINISHED |
| Object | British Army |
—
|
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: British Army | Statement: [National Volunteers, recruitmentChannelFor, British Army]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recruitmentChannelFor Context triple: [National Volunteers, recruitmentChannelFor, British Army]
-
A.
recruitmentFrom
Indicates that one entity recruits or sources members, employees, or participants from another entity.
-
B.
recruitmentPlatform
chosen
Indicates a relationship where an entity serves as a platform or medium used to recruit or attract candidates for positions or roles.
-
C.
recruitsFor
Indicates that one entity actively seeks out, enlists, or brings in participants, members, or resources on behalf of another entity, such as an organization, event, or cause.
-
D.
recruitmentBase
Indicates the foundational source, location, or context from which recruitment efforts or recruited entities originate.
-
E.
recruitingFocus
Indicates that an entity’s recruitment efforts are specifically directed toward or concentrated on another entity or group.
- 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_69f76e2190f88190beb2eed798a4ef01 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7aa3edb788190b9cb3760419ab7de |
completed | May 3, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69f7a8d435288190b30b1991fb003121 |
completed | May 3, 2026, 7:58 p.m. |
Created at: May 3, 2026, 4:06 p.m.