Triple
T22875379
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Friend of the Devil |
E567306
|
entity |
| Predicate | hasNotableLiveVersions |
P85821
|
FINISHED |
| Object | Grateful Dead concerts |
—
|
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: Grateful Dead concerts | Statement: [Friend of the Devil, hasNotableLiveVersions, Grateful Dead concerts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNotableLiveVersions Context triple: [Friend of the Devil, hasNotableLiveVersions, Grateful Dead concerts]
-
A.
hasLiveVersions
Indicates that an entity has one or more recorded or documented live-performance versions of itself.
-
B.
hasNotableVersion
Indicates that an entity has a specific version or variant that is particularly significant, distinguished, or noteworthy compared to other versions.
-
C.
isLiveVersion
Indicates that one entity is the current, active, or publicly available version of another entity.
-
D.
hasLiveActionVersion
Indicates that an entity has a corresponding adaptation or version produced in live-action (with real actors and physical settings) rather than animation or other non-live formats.
-
E.
notableLiveVersion
chosen
Indicates that one work is a particularly significant or well-known live performance version of another work.
- 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_69e24589d8348190b96422d13a678bc1 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17f57a1ec8190b8c6a0080d97a2a2 |
completed | April 29, 2026, 3:47 a.m. |
| PD | Predicate disambiguation | batch_69eed2d8c0608190afef4c4e530c0e2c |
completed | April 27, 2026, 3:07 a.m. |
Created at: April 17, 2026, 3:39 p.m.