Triple
T10280273
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geoff Bent |
E241079
|
entity |
| Predicate | hasPartInCuriculum |
P24108
|
FINISHED |
| Object | history of Manchester United F.C. |
—
|
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: history of Manchester United F.C. | Statement: [Geoff Bent, hasPartInCuriculum, history of Manchester United F.C.]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPartInCuriculum Context triple: [Geoff Bent, hasPartInCuriculum, history of Manchester United F.C.]
-
A.
hasCurriculumComponent
chosen
Indicates that one curriculum or educational program includes or is composed of a particular component, module, or element.
-
B.
hasCurriculumArea
Indicates that an educational program, course, or learning activity is associated with a specific curriculum area or subject domain.
-
C.
usesCurriculum
Indicates that one entity adopts or applies a particular curriculum as the basis for its instruction, training, or educational activities.
-
D.
hasStructureOnCourse
Indicates that a physical structure is located on, along, or directly associated with a specific course or route.
-
E.
isCourse
Indicates that an entity functions as or qualifies as a course within a given context 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_69d381a94c1881908fc38fc263d9b9c2 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d7ccb7ec8190a538cf279e48116e |
completed | April 7, 2026, 10:09 a.m. |
| PD | Predicate disambiguation | batch_69d4d1f117708190928f92ae2611d724 |
completed | April 7, 2026, 9:44 a.m. |
Created at: April 6, 2026, 11:38 a.m.