Triple
T7685117
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1996 United States House of Representatives elections |
E174095
|
entity |
| Predicate | chamberNumberElected |
P78701
|
FINISHED |
| Object | 105 |
—
|
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: 105 | Statement: [1996 United States House of Representatives elections, chamberNumberElected, 105]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chamberNumberElected Context triple: [1996 United States House of Representatives elections, chamberNumberElected, 105]
-
A.
electedChamber
Indicates that an individual has been chosen through an election to serve as a member of a specific legislative chamber.
-
B.
electsToChamber
Indicates that a group or body selects or votes individuals into membership of a specific legislative chamber.
-
C.
chamberOf
Indicates that one entity is a chamber, room, or enclosed space that is part of, contained within, or assigned to another entity.
-
D.
representsChamber
Indicates that one entity serves as or functions as a chamber (such as a room, compartment, or legislative body) associated with another entity.
-
E.
forChamber
Indicates that something is intended for use in, associated with, or belonging to a particular chamber.
- 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_69c6995840408190a19de6c51090f46f |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c706d1f0208190bc5b695aa5736244 |
completed | March 27, 2026, 10:38 p.m. |
| PD | Predicate disambiguation | batch_69c70163dea88190ae729df50e63dfd7 |
completed | March 27, 2026, 10:15 p.m. |
| PDg | Predicate description generation | batch_69c706d0c1708190a3e74523997814b8 |
completed | March 27, 2026, 10:38 p.m. |
Created at: March 27, 2026, 4:02 p.m.