Triple
T5254557
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pekar |
E118666
|
entity |
| Predicate | relatedToOccupation |
P2374
|
FINISHED |
| Object | baking |
—
|
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: baking | Statement: [Pekar, relatedToOccupation, baking]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedToOccupation Context triple: [Pekar, relatedToOccupation, baking]
-
A.
relatedProfession
Indicates that two entities have professions that are connected or associated in some meaningful way, such as being in the same field, industry, or professional domain.
-
B.
workRelatedTo
Indicates a relationship where one entity’s work, tasks, or professional activities are connected, associated, or relevant to those of another entity.
-
C.
relationToIndustry
Indicates how an entity is connected or relevant to a particular industry, such as through involvement, impact, or association.
-
D.
requiredOccupationOf
Indicates that one entity specifies the occupation or job role that is required or expected for another entity (such as a position, task, or qualification).
-
E.
subjectOccupation
chosen
Indicates that the subject holds or performs a particular job, profession, or role as their occupation.
- 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_69bd446978108190bb5f9c5c23d93f88 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7ba1cca88190bebd516851b9bf7f |
completed | March 20, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_69bd77c30bac8190a883ca45da35d667 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:50 p.m.