Triple
T35909761
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charles Townsend |
E1038572
|
entity |
| Predicate | agencyName |
P183962
|
FINISHED |
| Object | Townsend Agency |
—
|
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: Townsend Agency | Statement: [Charles Townsend, agencyName, Townsend Agency]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: agencyName Context triple: [Charles Townsend, agencyName, Townsend Agency]
-
A.
componentAgency
Indicates that one entity functions as a constituent or subordinate agency within the organizational structure of another agency.
-
B.
sponsoringAgency
Indicates that one entity serves as the sponsoring agency that provides support, backing, or authorization for another entity or activity.
-
C.
publicAgency
Indicates that an entity functions as a government-controlled or government-authorized organization that provides public services or carries out public administration.
-
D.
stateAgencyOf
Indicates that one entity is a governmental agency that operates under the authority or jurisdiction of a particular state.
-
E.
managingAgencyAbbreviation
Indicates that one entity is identified by the abbreviated name of the agency responsible for managing or overseeing it.
- 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_69f76e2259608190bf6788a132e0d139 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7aaabb58c8190bf81673608ecfb6e |
completed | May 3, 2026, 8:06 p.m. |
| PD | Predicate disambiguation | batch_69f7a8d435288190b30b1991fb003121 |
completed | May 3, 2026, 7:58 p.m. |
| PDg | Predicate description generation | batch_69f7aa33e0488190a135166bb67e1118 |
completed | May 3, 2026, 8:04 p.m. |
Created at: May 3, 2026, 4:07 p.m.