Triple
T12776845
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tokai |
E305398
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Constantia |
E884206
|
NE 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: Constantia | Statement: [Tokai, locatedNear, Constantia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Constantia Context triple: [Tokai, locatedNear, Constantia]
-
A.
Constantia
Constantia was a Roman noblewoman, traditionally identified as a daughter or close relative of Emperor Constantine the Great, after whom the city of Constanța is believed to be named.
-
B.
Constantia
chosen
Constantia is an affluent, historic suburb of Cape Town renowned for its wine estates, leafy scenery, and upmarket residential character.
-
C.
Palatino
Palatino is a widely used humanist serif typeface designed by Hermann Zapf, known for its readability and classical elegance in both print and digital typography.
-
D.
Didot
Didot is a family of neoclassical serif typefaces, created in late 18th-century France, known for their high contrast, vertical stress, and refined elegance widely used in fashion and luxury branding.
-
E.
Avenir
Avenir is Buick’s top-tier luxury sub-brand and trim line, offering more premium materials, advanced features, and upscale styling than the brand’s standard models.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d7bdf2b43c819098ae5aa68e61ea58 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96e595e008190b42dff3012d17d66 |
completed | April 10, 2026, 9:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f684fee60c81909245d4d70c9338c0 |
completed | May 2, 2026, 11:13 p.m. |
Created at: April 9, 2026, 5:29 p.m.