Triple
T20892199
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Delta Canis Majoris |
E514435
|
entity |
| Predicate | hasProperName |
P27536
|
FINISHED |
| Object | Wezen |
—
|
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: Wezen | Statement: [Delta Canis Majoris, hasProperName, Wezen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wezen Context triple: [Delta Canis Majoris, hasProperName, Wezen]
-
A.
Wezen
chosen
Wezen is a bright supergiant star in the constellation Canis Major, notable as one of its most luminous members.
-
B.
Woensel
Woensel is a large residential district in the northern part of the Dutch city of Eindhoven, known for its diverse population and extensive post-war housing.
-
C.
De Doorns
De Doorns is a town in South Africa’s Western Cape known for its table grape farming and location in the Hex River Valley.
-
D.
Vleteren
Vleteren is a rural municipality in the Belgian province of West Flanders, known for its quiet countryside and traditional Flemish character.
-
E.
Zesgehuchten
Zesgehuchten was a former village and municipality in the Dutch province of North Brabant, now part of the city of Geldrop-Mierlo.
- 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_69e0b4f7ebe48190952a85547a0f31a1 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6d05f0bec8190a296db546bd34114 |
completed | April 21, 2026, 1:18 a.m. |
Created at: April 16, 2026, 12:46 p.m.