Triple
T33738927
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jonathan Harvey |
E864505
|
entity |
| Predicate | adaptedHisOwnWork |
P179975
|
FINISHED |
| Object | Beautiful Thing (film adaptation screenplay) |
—
|
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: Beautiful Thing (film adaptation screenplay) | Statement: [Jonathan Harvey, adaptedHisOwnWork, Beautiful Thing (film adaptation screenplay)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: adaptedHisOwnWork Context triple: [Jonathan Harvey, adaptedHisOwnWork, Beautiful Thing (film adaptation screenplay)]
-
A.
adaptedWorkOfAuthor
Indicates that a work is an adaptation derived from, based on, or reinterpreting the original work of a specified author.
-
B.
adaptedWorkOf
Indicates that one work is derived from, based on, or reinterprets the content of another pre-existing work.
-
C.
adaptedIntoWork
Indicates that an original work has been transformed or re-created into another work, typically in a different medium or format.
-
D.
collaboratedOnAdaptationOf
Indicates that two or more entities worked together on creating or producing an adaptation of an existing work.
-
E.
adaptedWorkEdited
Indicates that an adapted work has been modified or revised through an editorial process.
- F. None of above. chosen
Provenance (4 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_69f3498b24b8819096a65009e521d0e1 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f72921cf2c8190909bb53f78bcc890 |
completed | May 3, 2026, 10:53 a.m. |
| PD | Predicate disambiguation | batch_69f7283d8cec8190b524c144948bc4ec |
completed | May 3, 2026, 10:49 a.m. |
| PDg | Predicate description generation | batch_69f72920c6208190aa4aba6cb6193109 |
completed | May 3, 2026, 10:53 a.m. |
Created at: May 1, 2026, 1:44 a.m.