Triple
T28669408
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Halloran House |
E725668
|
entity |
| Predicate | primaryBackdropOf |
P121009
|
FINISHED |
| Object | The Sundial |
—
|
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: The Sundial | Statement: [Halloran House, primaryBackdropOf, The Sundial]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryBackdropOf Context triple: [Halloran House, primaryBackdropOf, The Sundial]
-
A.
primaryBackdropFor
chosen
Indicates that one entity serves as the main visual or contextual background element for another entity.
-
B.
formsBackdropOf
Indicates that one entity serves as the background or setting against which another entity is viewed, occurs, or is presented.
-
C.
hasBackdrops
Indicates that one entity is associated with one or more background images or scenes used as visual backdrops for it.
-
D.
backedFilm
Indicates that one entity provided financial or promotional support for the production or distribution of a film.
-
E.
primaryCinema
Indicates that one entity is the main or most significant cinema associated with another entity (such as a person, work, or event).
- 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_69f01d85be388190b669a0e401e2f2c4 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_6a0064f8efa48190956287f548a8057d |
completed | May 10, 2026, 10:59 a.m. |
| PD | Predicate disambiguation | batch_6a006471e75c8190adae99bd75e7411b |
completed | May 10, 2026, 10:56 a.m. |
Created at: April 28, 2026, 5:02 a.m.