Triple
T33762539
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apocryphon: Electro Roots 1982–1985 |
E865149
|
entity |
| Predicate | featuresEarlyRecordingsOf |
P86042
|
FINISHED |
| Object | Information Society |
E246875
|
NE 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: Information Society | Statement: [Apocryphon: Electro Roots 1982–1985, featuresEarlyRecordingsOf, Information Society]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresEarlyRecordingsOf Context triple: [Apocryphon: Electro Roots 1982–1985, featuresEarlyRecordingsOf, Information Society]
-
A.
containsEarlyBandRecordings
chosen
Indicates that something includes recordings made by a band during its early period or formative years.
-
B.
recordingsKnownAs
Indicates that one recording is known, referred to, or identified by a particular alternative name or title.
-
C.
firstRecordedWith
Indicates that an entity’s earliest known or documented occurrence is associated with a specified context, source, or accompanying entity.
-
D.
recordingsFrom
Indicates a relationship where one entity serves as the source or origin of recordings that are associated with or derived from it.
-
E.
oftenRecordedIn
Indicates that instances of one entity are frequently documented, logged, or captured within another entity (such as a medium, dataset, or record).
- F. None of above.
Provenance (4 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_69f3498d3b748190aa3c4006c1f32f38 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a02145017b08190bd424cc647c08d3b |
completed | May 11, 2026, 5:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3872607284819086f49208a9338bf1 |
completed | June 21, 2026, 11:23 p.m. |
| PD | Predicate disambiguation | batch_6a021338e2b08190980c489ee44c18b3 |
completed | May 11, 2026, 5:34 p.m. |
Created at: May 1, 2026, 1:45 a.m.