Triple
T30251328
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Democratic Senatorial Campaign Committee |
E769208
|
entity |
| Predicate | chamber focus |
P61483
|
FINISHED |
| Object | United States Senate |
—
|
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 Senate | Statement: [Democratic Senatorial Campaign Committee, chamber focus, United States Senate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chamber focus Context triple: [Democratic Senatorial Campaign Committee, chamber focus, United States Senate]
-
A.
chamber1
Indicates that an entity is a chamber or room, typically serving as an enclosed space within a larger structure.
-
B.
chamber2
Indicates that one entity serves as a secondary or inner chamber, room, or compartment associated with another entity.
-
C.
chamberTargeted
Indicates that a specific chamber or compartment is the intended focus or recipient of an action, effect, or operation.
-
D.
forChamber
chosen
Indicates that something is intended for use in, associated with, or belonging to a particular chamber.
-
E.
chamberOf
Indicates that one entity is a chamber, room, or enclosed space that is part of, contained within, or assigned to another entity.
- 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_69f224831dc08190b2e569b987264057 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6807c31608190b1c5831c6035dba4 |
completed | May 2, 2026, 10:53 p.m. |
| PD | Predicate disambiguation | batch_69f6760216108190bbb708d53a6c2c25 |
completed | May 2, 2026, 10:09 p.m. |
Created at: April 29, 2026, 7:40 p.m.