Triple
T21743581
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Brother |
E536725
|
entity |
| Predicate | hasOccupationOnEarth |
P14167
|
FINISHED |
| Object | arcade repairman |
—
|
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: arcade repairman | Statement: [The Brother, hasOccupationOnEarth, arcade repairman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOccupationOnEarth Context triple: [The Brother, hasOccupationOnEarth, arcade repairman]
-
A.
hasHumanOccupationEvidence
Indicates that there is supporting evidence that a human has held or currently holds a particular occupation or job role.
-
B.
occupationOf
chosen
Indicates that one entity holds or performs the job, role, or profession associated with another entity.
-
C.
endedOccupationOf
Indicates that one entity brought another entity’s occupation or control of a place or position to an end.
-
D.
hasOccupationRelative
Indicates that one entity has another entity as a relative who holds a particular occupation or job.
-
E.
hasOccupationInWork
Indicates that an entity holds or performs a specific occupation within a particular work, project, or creative production.
- 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_69e0c46df5448190b4322127ffc4c690 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f01a74592c8190959af631d72df479 |
completed | April 28, 2026, 2:24 a.m. |
| PD | Predicate disambiguation | batch_69e6969c16fc8190b5126c169317d85d |
completed | April 20, 2026, 9:11 p.m. |
Created at: April 16, 2026, 6:49 p.m.