Triple
T10434340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Forest Hills, Washington, D.C. |
E245998
|
entity |
| Predicate | representedInCouncilBy |
P27096
|
FINISHED |
| Object | Ward 3 councilmember |
—
|
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: Ward 3 councilmember | Statement: [Forest Hills, Washington, D.C., representedInCouncilBy, Ward 3 councilmember]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: representedInCouncilBy Context triple: [Forest Hills, Washington, D.C., representedInCouncilBy, Ward 3 councilmember]
-
A.
hasCouncilSeat
Indicates that an entity holds a position or seat on a governing council.
-
B.
areRepresentedIn
Indicates that one entity serves as a representation, depiction, or encoding of another entity within a given medium, context, or system.
-
C.
representedInNationalAssembly
Indicates that an entity has official representation or a seat in a country's national legislative assembly.
-
D.
representedInProvincialLegislatureBy
chosen
Indicates that a geographic or political area is politically represented by a specific member or body in a provincial legislature.
-
E.
positionOnCouncils
Indicates that an entity holds a seat or role as a member on one or more councils.
- 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_69d381bf3dc08190bf35a2643e4e8f22 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4ea67344c81909984ab99b0ef1e64 |
completed | April 7, 2026, 11:28 a.m. |
| PD | Predicate disambiguation | batch_69d4dfbc546881908f312c66ee195f79 |
completed | April 7, 2026, 10:43 a.m. |
Created at: April 6, 2026, 12:14 p.m.