Triple
T18828446
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yaghi-Siyan |
E460455
|
entity |
| Predicate | controlled |
P4700
|
FINISHED |
| Object | city of Antioch |
—
|
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: city of Antioch | Statement: [Yaghi-Siyan, controlled, city of Antioch]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: city of Antioch Context triple: [Yaghi-Siyan, controlled, city of Antioch]
-
A.
Antioche
Antioche is a figure from Greek mythology known primarily as the wife of the hero Eurytus.
-
B.
Antioch on the Orontes
chosen
Antioch on the Orontes was a major ancient city in Syria that became a leading political, commercial, and cultural center of the Hellenistic and later Roman worlds.
-
C.
Antioch
Antioch was the former name of the small rural community now known as Louvale in Stewart County, Georgia.
-
D.
Antioch
Antioch was an important ancient city in Syria that became a major center of early Christianity and missionary activity.
-
E.
Antiochia ad Cragum
Antiochia ad Cragum is an ancient Roman-era city on Turkey’s Mediterranean coast, noted for its well-preserved ruins including baths, mosaics, and fortifications.
- 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_69d8dcf94c288190a06dea029ae4b223 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5a99554848190933dd2810f5c810f |
completed | April 20, 2026, 4:20 a.m. |
Created at: April 10, 2026, 11:56 a.m.