Triple
T24798506
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 34th Canadian Parliament |
E620455
|
entity |
| Predicate | chamberSpeaker |
P46769
|
FINISHED |
| Object | Speaker of the House of Commons John Fraser |
—
|
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: Speaker of the House of Commons John Fraser | Statement: [34th Canadian Parliament, chamberSpeaker, Speaker of the House of Commons John Fraser]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chamberSpeaker Context triple: [34th Canadian Parliament, chamberSpeaker, Speaker of the House of Commons John Fraser]
-
A.
chamberOf
Indicates that one entity is a chamber, room, or enclosed space that is part of, contained within, or assigned to another entity.
-
B.
forChamber
Indicates that something is intended for use in, associated with, or belonging to a particular chamber.
-
C.
partOfChamber
Indicates that one entity is a component or section within a larger chamber or enclosed space.
-
D.
speakerChamber
chosen
Indicates the legislative chamber or house in which a given speaker holds or held their official position.
-
E.
representedChamber
Indicates that one entity served as the legislative chamber or house in which another entity (such as a person or office) held representation or a seat.
- 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_69e2fabe77c8819085f7ce6486248139 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f44a417a58819081777e18dda149fd |
completed | May 1, 2026, 6:37 a.m. |
| PD | Predicate disambiguation | batch_69f442a977b08190b44eac040cb90211 |
completed | May 1, 2026, 6:05 a.m. |
Created at: April 18, 2026, 4:49 a.m.