Triple
T32350504
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gibson Hummingbird |
E826579
|
entity |
| Predicate | famousUsers |
P161890
|
FINISHED |
| Object | Keith Richards |
—
|
NE NERFINISHED |
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: Keith Richards | Statement: [Gibson Hummingbird, famousUsers, Keith Richards]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: famousUsers Context triple: [Gibson Hummingbird, famousUsers, Keith Richards]
-
A.
notableUser
Indicates that the user holds a special or distinguished status, such as being recognized, influential, or otherwise noteworthy within a given context.
-
B.
followersKnownAs
Indicates that the followers of an entity are referred to by a particular name or label.
-
C.
famousIndividual
Indicates that an individual is widely known and recognized by a large number of people, typically for notable achievements, status, or public visibility.
-
D.
peopleRecognizedAs
chosen
Indicates that certain individuals are acknowledged or identified as having a particular status, role, or identity in relation to something or someone.
-
E.
famousModel
Indicates that the subject is a well-known or widely recognized model.
- 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_69f34914dfc48190a390cd0720d9e86f |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6be56d7908190a730ed6da60acffd |
completed | May 3, 2026, 3:17 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6cef208190bc5cd43d96127004 |
completed | May 3, 2026, 3:01 a.m. |
Created at: May 1, 2026, 12:49 a.m.