Triple
T16496752
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Comana in Pontus |
E400701
|
entity |
| Predicate | modernSiteNear |
P8489
|
FINISHED |
| Object |
Gümenek
Gümenek is a modern locality in northern Turkey identified as the site of the ancient city of Comana in Pontus.
|
E1216482
|
NE FINISHED |
How this triple was built (4 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: Gümenek | Statement: [Comana in Pontus, modernSiteNear, Gümenek]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gümenek Context triple: [Comana in Pontus, modernSiteNear, Gümenek]
-
A.
Taibach
Taibach is a residential area and community within the county borough of Neath Port Talbot in South Wales, historically associated with the steel industry and the town of Port Talbot.
-
B.
Zachenberg
Zachenberg is a small municipality in the Bavarian Forest region of southeastern Germany.
-
C.
Reichenau
Reichenau is a German municipality best known for its UNESCO-listed monastic island on Lake Constance, renowned for its medieval abbey and cultural heritage.
-
D.
Reichenau
Reichenau is a locality in the Swiss canton of Graubünden known as the meeting point of the Vorderrhein and Hinterrhein rivers, which together form the Rhine.
-
E.
Unterberken
Unterberken is a small village and district of the town of Schorndorf in the German state of Baden-Württemberg.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Gümenek Triple: [Comana in Pontus, modernSiteNear, Gümenek]
Generated description
Gümenek is a modern locality in northern Turkey identified as the site of the ancient city of Comana in Pontus.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Gümenek Target entity description: Gümenek is a modern locality in northern Turkey identified as the site of the ancient city of Comana in Pontus.
-
A.
Taibach
Taibach is a residential area and community within the county borough of Neath Port Talbot in South Wales, historically associated with the steel industry and the town of Port Talbot.
-
B.
Zachenberg
Zachenberg is a small municipality in the Bavarian Forest region of southeastern Germany.
-
C.
Reichenau
Reichenau is a German municipality best known for its UNESCO-listed monastic island on Lake Constance, renowned for its medieval abbey and cultural heritage.
-
D.
Reichenau
Reichenau is a locality in the Swiss canton of Graubünden known as the meeting point of the Vorderrhein and Hinterrhein rivers, which together form the Rhine.
-
E.
Unterberken
Unterberken is a small village and district of the town of Schorndorf in the German state of Baden-Württemberg.
- F. None of above. chosen
Provenance (5 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_69d88381f6148190819958a038be990e |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32e343a7c81909e04cbaaa40e2531 |
completed | April 18, 2026, 7:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a005828849481909e95c5822ed6f74d |
completed | May 10, 2026, 10:04 a.m. |
| NEDg | Description generation | batch_6a00596390e4819091909806772afa1a |
completed | May 10, 2026, 10:09 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a005a0baef08190b77423fe81a7a11c |
completed | May 10, 2026, 10:12 a.m. |
Created at: April 10, 2026, 5:14 a.m.