Triple
T203207
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madam Speaker |
E4551
|
entity |
| Predicate | usedInChamber |
P1126
|
FINISHED |
| Object | House chamber of the U.S. Capitol |
—
|
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: House chamber of the U.S. Capitol | Statement: [Madam Speaker, usedInChamber, House chamber of the U.S. Capitol]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedInChamber Context triple: [Madam Speaker, usedInChamber, House chamber of the U.S. Capitol]
-
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.
chamberType
Indicates the specific kind or category of chamber associated with an entity (e.g., room, compartment, or enclosed space type).
-
D.
chamberInvolved
chosen
Indicates that a particular chamber (e.g., legislative or judicial body) participates in, is affected by, or plays a role in the referenced event, process, or relationship.
-
E.
hasChamber
Indicates that one entity possesses, contains, or is associated with a distinct enclosed space or compartment (a chamber).
- 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_69a25737567c81908f9c505300239181 |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25f46b4f081909e5ee3718109a71f |
completed | Feb. 28, 2026, 3:21 a.m. |
| PD | Predicate disambiguation | batch_69a25b4b42ec8190bef16bbbdd30a742 |
completed | Feb. 28, 2026, 3:04 a.m. |
Created at: Feb. 28, 2026, 2:51 a.m.