Triple
T26888949
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Glass Key (1942 film) |
E677119
|
entity |
| Predicate | featuresOnscreenPartnership |
P35556
|
FINISHED |
| Object | Alan Ladd and Veronica Lake |
—
|
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: Alan Ladd and Veronica Lake | Statement: [The Glass Key (1942 film), featuresOnscreenPartnership, Alan Ladd and Veronica Lake]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresOnscreenPartnership Context triple: [The Glass Key (1942 film), featuresOnscreenPartnership, Alan Ladd and Veronica Lake]
-
A.
featuresOnscreenPairing
chosen
Indicates that two entities appear together as an on-screen pairing within the same visual or filmed context.
-
B.
hasOnscreenPartner
Indicates that one entity appears together with another as a partner within the same onscreen context or scene.
-
C.
primaryPartners
Indicates that the entities are each other’s main or most significant partners in a relationship, typically implying priority or exclusivity over other partnerships.
-
D.
featuresSign
Indicates that an entity includes, displays, or incorporates a particular sign as part of its appearance, content, or design.
-
E.
featuresMode
Indicates that one entity operates in, supports, or is characterized by a particular mode or configuration specified by another entity.
- 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_69eee9bc0c90819085608c8bdc513a57 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69fcf1b3d9a08190850b388308656266 |
completed | May 7, 2026, 8:10 p.m. |
| PD | Predicate disambiguation | batch_69fcf0226d8c8190b23dceafb1794995 |
completed | May 7, 2026, 8:03 p.m. |
Created at: April 27, 2026, 5:43 a.m.