Triple
T1793814
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blade Runner (film score) |
E39557
|
entity |
| Predicate | hasFanRelease |
P18289
|
FINISHED |
| Object | bootleg editions prior to official album |
—
|
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: bootleg editions prior to official album | Statement: [Blade Runner (film score), hasFanRelease, bootleg editions prior to official album]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFanRelease Context triple: [Blade Runner (film score), hasFanRelease, bootleg editions prior to official album]
-
A.
hasRelease
Indicates that an entity (such as a product, work, or version) has a specific release instance or event associated with it.
-
B.
hasFanActivity
chosen
Indicates that an entity is associated with actions, behaviors, or engagement carried out by fans in relation to it.
-
C.
hasReleaseModel
Indicates the type or strategy of release associated with an entity, such as how or under what model it is made available.
-
D.
hasFanPerception
Indicates that an entity is perceived, interpreted, or regarded in a particular way by its fans or fan community.
-
E.
releasedBy
Indicates that something (such as a product, work, or item) is made available, issued, or launched by a particular agent or organization.
- 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_69a88631854081909723959921e45c2b |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69ab61b6ea188190aab9fb839bf1e367 |
completed | March 6, 2026, 11:22 p.m. |
| PD | Predicate disambiguation | batch_69aa61d2f7a8819090301f92d3e358c7 |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:32 p.m.