Triple
T29133688
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Colonel Sun |
E738448
|
entity |
| Predicate | setAfterWorksBy |
P71402
|
FINISHED |
| Object | Ian Fleming |
—
|
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: Ian Fleming | Statement: [Colonel Sun, setAfterWorksBy, Ian Fleming]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: setAfterWorksBy Context triple: [Colonel Sun, setAfterWorksBy, Ian Fleming]
-
A.
setAfterWork
Indicates that one event, state, or action is scheduled or configured to occur after the completion of work or working hours.
-
B.
afterAWorkBy
Indicates that one work is created subsequent to and based on, inspired by, or derived from another existing work.
-
C.
workAfter
Indicates that one entity performs its work or begins an activity only after another specified entity has completed or started its own work.
-
D.
laterWorkBy
chosen
Indicates that one work was created after another work by the same creator or author.
-
E.
setInWorkBy
Indicates that something (such as a scene, event, or element) is situated or occurs within the context or setting of a particular work (such as a book, film, or other creative production).
- 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_69f07cb3adb48190a9e0e169cd026634 |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f6622f519881909a265ebf46433064 |
completed | May 2, 2026, 8:44 p.m. |
| PD | Predicate disambiguation | batch_69f65c2376a08190be5215171e908e69 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 11:33 a.m.