Triple
T12950749
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cretan School |
E309884
|
entity |
| Predicate | center |
P4751
|
FINISHED |
| Object | Candia |
E345674
|
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: Candia | Statement: [Cretan School, center, Candia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Candia Context triple: [Cretan School, center, Candia]
-
A.
Candia
chosen
Candia is the former Venetian and historical name for the city now known as Heraklion, the capital of the Greek island of Crete.
-
B.
Corabia
Corabia is a small town in southern Romania, situated on the Danube River in Olt County and known historically as a local port and agricultural center.
-
C.
Kluuvi
Kluuvi is a central district of Helsinki, Finland, known as the city’s main commercial and business hub.
-
D.
Corisande
Corisande is a noble lady and love interest in the medieval chivalric romance cycle "Amadis de Gaula."
-
E.
Lierne
Lierne is a sparsely populated municipality in Trøndelag county, Norway, known for its vast wilderness areas, national parks, and rich wildlife.
- 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_69d7bdfb57a88190836b743e2825feca |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97e1dc4c88190ab27b832d6a7c556 |
completed | April 10, 2026, 10:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6af7790808190826f98e8aff01523 |
completed | May 3, 2026, 2:14 a.m. |
Created at: April 9, 2026, 5:43 p.m.