Triple
T24599631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarah Walker |
E608785
|
entity |
| Predicate | coverJob |
P109187
|
FINISHED |
| Object | employee at the Orange Orange yogurt shop |
—
|
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: employee at the Orange Orange yogurt shop | Statement: [Sarah Walker, coverJob, employee at the Orange Orange yogurt shop]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coverJob Context triple: [Sarah Walker, coverJob, employee at the Orange Orange yogurt shop]
-
A.
dreamJob
Indicates that one entity is the ideal or highly desired job or occupation of another entity.
-
B.
coversOccupation
Indicates that one entity provides information about, includes, or pertains to another entity’s occupation or professional role.
-
C.
cover
Indicates that one entity extends over, conceals, protects, or provides a surface or layer for another entity.
-
D.
coverRole
chosen
Indicates that one entity temporarily assumes or fills the role, duties, or position normally held by another entity.
-
E.
workCovered
Indicates that one work or effort is included within the scope, protection, or responsibility defined by another entity or arrangement.
- 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_69e2c4cf54248190af7b0c2d9ade9830 |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2be044d4c819094e14eda28d371a7 |
completed | April 30, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f2a6ca751c8190a040c10d701ecf3a |
completed | April 30, 2026, 12:48 a.m. |
Created at: April 18, 2026, 2:30 a.m.