Triple
T22154009
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bronckhorst |
E547485
|
entity |
| Predicate | mayorParty |
P352
|
FINISHED |
| Object | CDA |
—
|
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: CDA | Statement: [Bronckhorst, mayorParty, CDA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CDA Context triple: [Bronckhorst, mayorParty, CDA]
-
A.
CDA
CDA is the Capital Development Authority, the municipal and development agency responsible for planning and managing Islamabad, Pakistan’s capital city.
-
B.
CDA
CDA (Clinical Document Architecture) is an HL7 standard for structuring and encoding clinical documents to enable interoperable exchange of healthcare information between systems.
-
C.
CDA
chosen
CDA is a major Dutch Christian-democratic political party that has frequently participated in governing coalitions in the Netherlands.
-
D.
CACD
CACD is the commonly used abbreviation for the United States District Court for the Central District of California, a federal trial court serving the central region of the state.
-
E.
CADA
CADA is a college focused on education and research in architecture, design, visual arts, and performing arts.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e3b52088190ad5df386d01eb2fb |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f129f6d5b88190badee2e515a3b633 |
completed | April 28, 2026, 9:43 p.m. |
Created at: April 16, 2026, 8:33 p.m.