Triple
T38182628
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Invictus Records |
E1005212
|
entity |
| Predicate | foundersRoleAtMotown |
P200140
|
FINISHED |
| Object | songwriters |
—
|
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: songwriters | Statement: [Invictus Records, foundersRoleAtMotown, songwriters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: foundersRoleAtMotown Context triple: [Invictus Records, foundersRoleAtMotown, songwriters]
-
A.
founderKnownFor
Indicates that a founder is particularly recognized or notable for a specific work, achievement, product, or contribution.
-
B.
foundingMemberAlongside
Indicates that an entity was a founding member of an organization or group together with one or more specified other entities at the time of its establishment.
-
C.
founderBirthName
Indicates the original personal name given at birth to the individual who founded an organization or entity.
-
D.
founderAlsoKnownAs
Indicates that an individual who is a founder of something is also known by an alternative name or alias.
-
E.
founderBirthPlace
Indicates the place where the founder of an entity was born.
- F. None of above. chosen
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_69f76dbc22c481908139b694ffde7a0c |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69ff76ac40988190a34d858b5472ee2b |
completed | May 9, 2026, 6:02 p.m. |
| PD | Predicate disambiguation | batch_69ff760a90948190a12fcb80e6e3e14b |
completed | May 9, 2026, 5:59 p.m. |
| PDg | Predicate description generation | batch_69ff76ab9b4c8190b4cc7c9c733b2765 |
completed | May 9, 2026, 6:02 p.m. |
Created at: May 3, 2026, 4:29 p.m.