Triple
T28211932
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | James Garner as Murphy Jones |
E711193
|
entity |
| Predicate | titleOfWorkDerivedFrom |
P88313
|
FINISHED |
| Object | Murphy Jones |
—
|
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: Murphy Jones | Statement: [James Garner as Murphy Jones, titleOfWorkDerivedFrom, Murphy Jones]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: titleOfWorkDerivedFrom Context triple: [James Garner as Murphy Jones, titleOfWorkDerivedFrom, Murphy Jones]
-
A.
titleDerivedFrom
Indicates that the title of one entity is obtained or adapted from another entity.
-
B.
originalWorkFrom
Indicates that something is derived, adapted, or based on an earlier original work created by another source.
-
C.
workFromWhichTitleDerived
chosen
Indicates that a title is derived from, or based on, a particular underlying work.
-
D.
originalWorkBy
Indicates that one entity is the creator or originator of another entity (such as a work, idea, or product).
-
E.
titleOfLargerWork
Indicates that one work is the larger or containing work (such as a book, journal, or collection) in which another, smaller work is included or published.
- 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_69efb51cb5288190818c1f63a266af11 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69fcf36d2894819089b7db8e91b63c9d |
completed | May 7, 2026, 8:17 p.m. |
| PD | Predicate disambiguation | batch_69fcf25c0a108190bfa823474098640b |
completed | May 7, 2026, 8:13 p.m. |
Created at: April 27, 2026, 10:40 p.m.