Triple
T2255722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Seidler |
E49718
|
entity |
| Predicate | basedScreenplayOn |
P15523
|
FINISHED |
| Object | the relationship between King George VI and Lionel Logue |
—
|
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: the relationship between King George VI and Lionel Logue | Statement: [David Seidler, basedScreenplayOn, the relationship between King George VI and Lionel Logue]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: basedScreenplayOn Context triple: [David Seidler, basedScreenplayOn, the relationship between King George VI and Lionel Logue]
-
A.
screenwriterOfWork
Indicates that a person served as the screenwriter (wrote the screenplay) for a particular creative work.
-
B.
screenplayBy
Indicates that a film, television show, or similar work was written or scripted by a particular person or group.
-
C.
screenWriterAdaptationBy
Indicates that a person served as the screenwriter responsible for adapting an existing work into a screenplay.
-
D.
screenplayType
Indicates the specific category or format of a screenplay associated with a work or production.
-
E.
adaptedWorkOf
chosen
Indicates that one work is derived from, based on, or reinterprets the content of another pre-existing work.
- 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_69a88aaa9250819095e127d0d77e8a32 |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc1559ff481908efe3f214b2570dc |
completed | March 7, 2026, 6:10 a.m. |
| PD | Predicate disambiguation | batch_69abbdb34c148190b51e99f540f97204 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:47 p.m.