Triple
T13397843
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Frank |
E319745
|
entity |
| Predicate | positionAtEmployer |
P47952
|
FINISHED |
| Object | assistant head coach of Brentford FC |
—
|
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: assistant head coach of Brentford FC | Statement: [Thomas Frank, positionAtEmployer, assistant head coach of Brentford FC]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionAtEmployer Context triple: [Thomas Frank, positionAtEmployer, assistant head coach of Brentford FC]
-
A.
positionInWork
Indicates the specific role, rank, or placement an entity holds within a larger work or structured composition.
-
B.
workPosition
chosen
Indicates the specific job role or position that an entity holds within an organization or workplace.
-
C.
stateOfEmployment
Indicates that one entity’s employment status or condition is defined in relation to another entity (such as an employer, position, or employment situation).
-
D.
positionOnEmploymentPolicy
Indicates the stance or viewpoint an entity holds regarding employment-related rules, practices, or policies.
-
E.
peakEmployment
Indicates that an entity has reached its highest level of employment or workforce size during a specified period.
- 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_69d806b943cc8190b6af624d385d7e12 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dba0d9e7348190844e11dd6cbd13b0 |
completed | April 12, 2026, 1:40 p.m. |
| PD | Predicate disambiguation | batch_69d9a03189908190a784a2755f8d81e1 |
completed | April 11, 2026, 1:13 a.m. |
Created at: April 9, 2026, 9:34 p.m.