Triple
T19844173
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Niksar |
E476813
|
entity |
| Predicate | historicalSiteOf |
P1098
|
FINISHED |
| Object | Neocaesarea |
—
|
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: Neocaesarea | Statement: [Niksar, historicalSiteOf, Neocaesarea]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Neocaesarea Context triple: [Niksar, historicalSiteOf, Neocaesarea]
-
A.
Neocaesarea in Pontus
chosen
Neocaesarea in Pontus was an important city in the Roman province of Pontus in Asia Minor, known as a regional center of early Christianity.
-
B.
Diocaesarea
Diocaesarea is the Roman-era name for the ancient Galilean city of Sepphoris, a major administrative and cultural center near Nazareth.
-
C.
Doliche
Doliche was an ancient city of Perrhaebia in northern Thessaly, Greece, known from classical historical and geographical sources.
-
D.
Theodosiopolis
Theodosiopolis was an important late Roman and Byzantine frontier city in eastern Anatolia, located at the site of modern Erzurum in present-day Turkey.
-
E.
Edessa
Edessa is a historic city in northern Greece renowned for its picturesque waterfalls and ancient heritage.
- 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_69d8e51d39d081909bcfafeaaf3d2fcc |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e658085a148190a305bde0897dfe84 |
completed | April 20, 2026, 4:44 p.m. |
Created at: April 10, 2026, 1:51 p.m.