Triple
T15683285
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | King of Pontus |
E377632
|
entity |
| Predicate | hasCapital |
P204
|
FINISHED |
| Object | Amasia |
E341655
|
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: Amasia | Statement: [King of Pontus, hasCapital, Amasia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amasia Context triple: [King of Pontus, hasCapital, Amasia]
-
A.
Amasia
chosen
Amasia (modern Amasya in Turkey) is an ancient city in northern Anatolia known as the early royal center of the Kingdom of Pontus and the birthplace of the geographer Strabo.
-
B.
Amasia
Amasia is a village located in Armenia’s Shirak Province, known for its rural setting in the country’s northwestern highlands.
-
C.
Planasia
Planasia was a small island off the coast of Italy used by the Romans as a place of political exile.
-
D.
Aasiaat
Aasiaat is a coastal town in western Greenland known for its fishing industry, colorful houses, and location amid the icebergs and wildlife-rich waters of the Arctic.
-
E.
Asianet
Asianet is a leading Malayalam-language television channel and entertainment network widely watched in the Indian state of Kerala and among the Malayali diaspora.
- 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_69d85cd2e28481909d4e975bee20872f |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04f31b5b881908e46ecd9fc6048ab |
completed | April 16, 2026, 2:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff6ee4c8688190ae2fefb56171161a |
completed | May 9, 2026, 5:29 p.m. |
Created at: April 10, 2026, 4:16 a.m.