Triple
T28047934
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dr. Tyrone Berger |
E708732
|
entity |
| Predicate | workRelationshipWith |
P20699
|
FINISHED |
| Object | Conrad Jarrett |
—
|
NE NERFINISHED |
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: Conrad Jarrett | Statement: [Dr. Tyrone Berger, workRelationshipWith, Conrad Jarrett]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workRelationshipWith Context triple: [Dr. Tyrone Berger, workRelationshipWith, Conrad Jarrett]
-
A.
employerRelationship
Indicates a relationship in which one entity acts as the employer of another, having authority to hire, direct, and compensate the other party for work performed.
-
B.
basedOnWorkRelationship
Indicates that one entity is derived from, adapted from, or otherwise created on the basis of another underlying work.
-
C.
workRelatedTo
chosen
Indicates a relationship where one entity’s work, tasks, or professional activities are connected, associated, or relevant to those of another entity.
-
D.
worksInCloseRelationshipWith
Indicates a collaborative professional relationship in which two or more entities work together closely and interact frequently to achieve shared goals.
-
E.
workTitleRelation
Indicates a relationship where one entity is the title or name of a work (such as a book, film, or artwork) associated with another entity.
- 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_69ef9b6df9f48190bbb971d02cbe1b65 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f63f3559148190bca6f6c3e45d3961 |
completed | May 2, 2026, 6:15 p.m. |
| PD | Predicate disambiguation | batch_69f63710d17c819084cfe96e6df334fd |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 8:31 p.m.