Triple
T11795005
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Troad |
E280482
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Sigeion |
E536163
|
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: Sigeion | Statement: [Troad, contains, Sigeion]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sigeion Context triple: [Troad, contains, Sigeion]
-
A.
Sigeion
chosen
Sigeion was an ancient Greek city in the Troad region near the entrance to the Hellespont, strategically important for controlling access to the Black Sea.
-
B.
Selinous
Selinous is an ancient town in the region of Cilicia, in what is now southern Turkey, known from classical antiquity.
-
C.
Siklós
Siklós is a historic town in southern Hungary known for its medieval castle and wine-producing region.
-
D.
Alexandretta
Alexandretta, historically known as İskenderun, is a strategic port city on Turkey’s Mediterranean coast that has long been a focal point of regional trade and territorial disputes.
-
E.
Eresos
Eresos is a historic coastal village on the Greek island of Lesbos, known as the birthplace of the ancient poet Sappho and for its scenic beaches.
- 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_69d6ab258b808190b1735835c841e3a4 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a5a082d08190a42541396a06ed98 |
completed | April 10, 2026, 7:24 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f0911c2a40819088079fc286e4dc67 |
completed | April 28, 2026, 10:51 a.m. |
Created at: April 8, 2026, 9:42 p.m.