Triple
T27367328
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hiro Matsuda |
E690202
|
entity |
| Predicate | workedInTerritory |
P19850
|
FINISHED |
| Object | Florida territory |
—
|
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: Florida territory | Statement: [Hiro Matsuda, workedInTerritory, Florida territory]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workedInTerritory Context triple: [Hiro Matsuda, workedInTerritory, Florida territory]
-
A.
activeInTerritory
chosen
Indicates that an entity conducts operations, activities, or maintains a presence within a specified geographic territory.
-
B.
workedAmong
Indicates that an individual carried out work or professional activities within a particular group, organization, or community.
-
C.
territoryCorrespondedTo
Indicates that one territory matched, aligned with, or was equivalent to another territory in scope, boundaries, or designation.
-
D.
operatesFromTerritory
Indicates that an entity conducts its activities or operations based out of, or primarily within, a specified territory.
-
E.
worksInCountry
Indicates that an entity performs its work or professional activities within the specified country.
- 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_69ef51ff826081909e42c8e2bfb97941 |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69f65876c52c8190bc889c7a67bd07f3 |
completed | May 2, 2026, 8:03 p.m. |
| PD | Predicate disambiguation | batch_69f6575d89788190aca478e4aea05a65 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 27, 2026, 12:17 p.m.