Triple
T28267872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Love, Lies and Murder |
E712755
|
entity |
| Predicate | hasAlternativeFormat |
P141530
|
FINISHED |
| Object | home video release |
—
|
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: home video release | Statement: [Love, Lies and Murder, hasAlternativeFormat, home video release]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAlternativeFormat Context triple: [Love, Lies and Murder, hasAlternativeFormat, home video release]
-
A.
hasAlternativeMedium
chosen
Indicates that an entity is available, expressed, or presented in another medium or format as an alternative to its primary one.
-
B.
hasAlternativeView
Indicates that one entity presents a different or contrasting perspective, interpretation, or representation relative to another entity.
-
C.
hasAlternativeArrangement
Indicates that one entity can be organized, configured, or structured in a different valid way as an alternative to its current or primary arrangement.
-
D.
hasAlternateEditionISBN
Indicates that one edition of a work is linked to another edition of the same work via its alternate ISBN.
-
E.
hasAlternativeRadioVersionWith
Indicates that one audio track has a corresponding alternative version specifically edited or mixed for radio play.
- 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_69efb5216c6881908020dce4aea65381 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f6db1f3ec48190a82e7d893d3c76ba |
completed | May 3, 2026, 5:20 a.m. |
| PD | Predicate disambiguation | batch_69f6d82adfa481908a5e196d2e18c73f |
completed | May 3, 2026, 5:07 a.m. |
Created at: April 27, 2026, 11:15 p.m.