Triple
T16324152
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Springfield Nuclear Power Plant |
E396370
|
entity |
| Predicate | jobTitleOfHomerSimpson |
P38167
|
FINISHED |
| Object | safety inspector |
—
|
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: safety inspector | Statement: [Springfield Nuclear Power Plant, jobTitleOfHomerSimpson, safety inspector]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: jobTitleOfHomerSimpson Context triple: [Springfield Nuclear Power Plant, jobTitleOfHomerSimpson, safety inspector]
-
A.
sonOccupation
Indicates that a specified occupation is the job or professional role held by a person's son.
-
B.
fatherOccupation
Indicates the type of job or profession held by a person's father.
-
C.
governmentOfficeOrTitleOf
Indicates that one entity is a government office or official title held by, associated with, or designating the role of another entity.
-
D.
titleOrRole
chosen
Indicates that one entity serves as the title, position, or role held or described by another entity.
-
E.
sonTitle
Indicates that the object is a title or form of address specifically associated with the subject in their role as a son.
- 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_69d87f255b788190a400eba031dd85d8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e296b8fe988190adee72b23246052f |
completed | April 17, 2026, 8:23 p.m. |
| PD | Predicate disambiguation | batch_69e219fc72c881909d452274e7af8238 |
completed | April 17, 2026, 11:31 a.m. |
Created at: April 10, 2026, 5:06 a.m.