Triple
T16195475
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lasithi Plateau |
E393049
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object | Kato Metochi |
E1361849
|
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: Kato Metochi | Statement: [Lasithi Plateau, hasSettlement, Kato Metochi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kato Metochi Context triple: [Lasithi Plateau, hasSettlement, Kato Metochi]
-
A.
Kato Metochi
chosen
Kato Metochi is a small village located on the Lasithi Plateau in eastern Crete, Greece.
-
B.
Jōtōmon-in
Jōtōmon-in was the honorary title of Empress Shōshi, a prominent consort of Emperor Ichijō and influential figure in the Heian-period Japanese imperial court.
-
C.
Kodai-in
Kodai-in, better known as Nene, was the principal wife of Toyotomi Hideyoshi and a prominent noblewoman who later became a respected Buddhist nun and patron of temples in Japan’s late Sengoku period.
-
D.
Kuon-ji
Kuon-ji is the head temple of Nichiren Buddhism, located on Mount Minobu in Yamanashi Prefecture, Japan.
-
E.
Kōtoku-in
Kōtoku-in is a Buddhist temple in Kamakura, Japan, best known for its monumental outdoor bronze statue of the Great Buddha (Daibutsu).
- 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_69d87f1e49ac8190a311b54d32990576 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e222d91130819080da4e2611612e27 |
completed | April 17, 2026, 12:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a06f89123f0819086f3aeef4c309f63 |
completed | May 15, 2026, 10:42 a.m. |
Created at: April 10, 2026, 5:02 a.m.