Triple
T36529607
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baxter family homestead |
E900404
|
entity |
| Predicate | publisherOfWorkLocation |
P1364
|
FINISHED |
| Object | United States |
—
|
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: United States | Statement: [Baxter family homestead, publisherOfWorkLocation, United States]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: publisherOfWorkLocation Context triple: [Baxter family homestead, publisherOfWorkLocation, United States]
-
A.
publisherLocation
chosen
Indicates the place or geographic location where a work is published or where its publisher is based.
-
B.
publisherOfWorkAppearingIn
Indicates that an entity is the publisher responsible for issuing a work in which another specified work appears (e.g., as part of a collection, volume, or compilation).
-
C.
employerOrPublisherOf
Indicates that one entity serves as the employer or publishing organization responsible for another entity (such as a person or work).
-
D.
publisherOfWorks
Indicates that one entity serves as the publisher responsible for issuing or distributing the works created by another entity.
-
E.
publisherWorkedFor
Indicates that a person was employed by or had a working relationship with a particular publishing organization.
- 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_69f76e5eedb88190a393b8c623f71dd7 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ffab5adf2c819084700c5ea34615bf |
completed | May 9, 2026, 9:47 p.m. |
| PD | Predicate disambiguation | batch_69ffaabffa208190b5214ca17cc8a5ea |
completed | May 9, 2026, 9:44 p.m. |
Created at: May 3, 2026, 4:11 p.m.