Triple
T16377124
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alâeddin Mosque (Konya) |
E397705
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object | Alaeddin Hill |
E89844
|
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: Alaeddin Hill | Statement: [Alâeddin Mosque (Konya), locatedOn, Alaeddin Hill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alaeddin Hill Context triple: [Alâeddin Mosque (Konya), locatedOn, Alaeddin Hill]
-
A.
Alaeddin Hill
chosen
Alaeddin Hill is a prominent historic mound and park in central Konya, Turkey, known for its ancient citadel ruins and panoramic views of the city.
-
B.
Sahr-i-Bahlol
Sahr-i-Bahlol is an ancient archaeological site in Pakistan renowned for its well-preserved remains of the Gandhara Buddhist civilization.
-
C.
Abu Kamal
Abu Kamal is a Syrian town on the Euphrates River near the Iraqi border, known as a key border crossing and trade route between Syria and Iraq.
-
D.
Khan-e Sanandaji
Khan-e Sanandaji is a historic traditional mansion in Sanandaj, Iran, noted for its Kurdish architectural style and cultural significance.
-
E.
Sikandra
Sikandra is a historic suburb of Agra in India best known for housing the grand mausoleum of the Mughal emperor Akbar.
- 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_69d87f2880b48190ae1a9673a3bbef80 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e319d8a40c8190af37e7ed60b9c4dd |
completed | April 18, 2026, 5:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00356406208190a9cedc1de2ab4e07 |
completed | May 10, 2026, 7:36 a.m. |
Created at: April 10, 2026, 5:08 a.m.