Triple
T23639743
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tunes of Glory |
E583850
|
entity |
| Predicate | hasJohnMillsRole |
P104626
|
FINISHED |
| Object | Lieutenant Colonel Basil Barrow |
—
|
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: Lieutenant Colonel Basil Barrow | Statement: [Tunes of Glory, hasJohnMillsRole, Lieutenant Colonel Basil Barrow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasJohnMillsRole Context triple: [Tunes of Glory, hasJohnMillsRole, Lieutenant Colonel Basil Barrow]
-
A.
hasJoanFontaineRole
Indicates that an entity has a role played by Joan Fontaine in a film, television, or theatrical production.
-
B.
hasPortrayedRole
chosen
Indicates that an entity has performed or depicted a specific role or character, typically in a work such as a film, play, or television show.
-
C.
hasHumanCast
Indicates that a work or production features human performers as part of its cast.
-
D.
hasJuliannePhillipsRoleType
Indicates that an entity has a role type specifically associated with Julianne Phillips in a given context or work.
-
E.
hasGingerRogersRole
Indicates that an entity is assigned or associated with a role specifically identified as the "Ginger Rogers" role in a given context or 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_69e248fe1c2c8190ac914d2442ff3d26 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b27fc22c8190abda7398b9fb928c |
completed | April 29, 2026, 7:25 a.m. |
| PD | Predicate disambiguation | batch_69f118d7903c8190bb590a71771e93af |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:48 p.m.