Triple
T7352146
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Assam Legislative Council |
E169526
|
entity |
| Predicate | typeOfChamber |
P76754
|
FINISHED |
| Object | indirectly elected upper chamber |
—
|
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: indirectly elected upper chamber | Statement: [Assam Legislative Council, typeOfChamber, indirectly elected upper chamber]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfChamber Context triple: [Assam Legislative Council, typeOfChamber, indirectly elected upper chamber]
-
A.
chamberType
Indicates the specific kind or category of chamber associated with an entity (e.g., room, compartment, or enclosed space type).
-
B.
chamber1
Indicates that an entity is a chamber or room, typically serving as an enclosed space within a larger structure.
-
C.
buildingTypeOfChamber
Indicates the type or category of building in which a given chamber is located or to which it belongs.
-
D.
chamber2
Indicates that one entity serves as a secondary or inner chamber, room, or compartment associated with another entity.
-
E.
typicalChamber
Indicates that something is a standard or characteristic chamber associated with a given context or entity.
- 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_69c68a5878888190968ce4d04db8d69f |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f139505c8190a7158cf59a6e089e |
completed | March 27, 2026, 9:06 p.m. |
| PD | Predicate disambiguation | batch_69c6f02aeeb8819099d1626566cec18b |
completed | March 27, 2026, 9:01 p.m. |
| PDg | Predicate description generation | batch_69c6f1379cac81908b35e617c44c7b13 |
completed | March 27, 2026, 9:05 p.m. |
Created at: March 27, 2026, 3:05 p.m.