Triple
T6128116
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Officers Training Academy |
E136641
|
entity |
| Predicate | targetIntake |
P42668
|
FINISHED |
| Object | graduate candidates |
—
|
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: graduate candidates | Statement: [Officers Training Academy, targetIntake, graduate candidates]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetIntake Context triple: [Officers Training Academy, targetIntake, graduate candidates]
-
A.
intake
Indicates the act of taking something in or consuming it, such as food, drink, or other substances, into a system or organism.
-
B.
nutritionMode
Indicates the way an entity obtains or processes nutrients for sustenance or growth.
-
C.
intakeLocation
chosen
Indicates the place or facility where an entity is initially received, admitted, or taken in.
-
D.
feedingStructure
Indicates a relationship where one entity serves as the anatomical or mechanical structure used by another entity to obtain or ingest food.
-
E.
largelyConsumedBy
Indicates that something is mostly or predominantly eaten or used up by a particular consumer 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_69c008a0a37c81908e5b4f879158afb3 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c05c4b1df081908dc87fa1c45a43bf |
completed | March 22, 2026, 9:16 p.m. |
| PD | Predicate disambiguation | batch_69c049fa905c8190b99eda54e9771b0b |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:15 p.m.