Triple
T4885461
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ghost Ranch |
E109428
|
entity |
| Predicate | usedAsSubjectIn |
P41975
|
FINISHED |
| Object | paintings by Georgia O’Keeffe |
—
|
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: paintings by Georgia O’Keeffe | Statement: [Ghost Ranch, usedAsSubjectIn, paintings by Georgia O’Keeffe]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedAsSubjectIn Context triple: [Ghost Ranch, usedAsSubjectIn, paintings by Georgia O’Keeffe]
-
A.
isUsedAs
Indicates that one entity serves a particular function, role, or purpose as another entity.
-
B.
usedAsExampleIn
chosen
Indicates that one entity is cited or presented as an illustrative example within another entity, such as a text, discussion, or explanation.
-
C.
hasSubjectPosition
Indicates that an entity occupies or is assigned to a particular subject role or position within a structure, context, or organization.
-
D.
hasSubjectPronouns
Indicates that an entity is associated with one or more pronouns that function as its grammatical subject in sentences.
-
E.
areUsedIn
Indicates that certain entities serve as components, tools, or resources within a particular process, context, or application.
- 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_69bd440f71348190b99938e59fb7f9a1 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6de3718881908521968fa6e6b444 |
completed | March 20, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69bd6c2be5e881909f6ec9c3bcde49f3 |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:27 p.m.