Triple
T12456944
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Al-Madina Souq |
E297682
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Khan al-Saboun |
E337843
|
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: Khan al-Saboun | Statement: [Al-Madina Souq, contains, Khan al-Saboun]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Khan al-Saboun Context triple: [Al-Madina Souq, contains, Khan al-Saboun]
-
A.
Khan al-Saboun
chosen
Khan al-Saboun is a historic soap market and caravanserai in Tripoli, Lebanon, renowned for its traditional production and trade of olive oil–based soaps.
-
B.
Khan al-Umdan
Khan al-Umdan is a well-preserved 18th-century Ottoman caravanserai in the Old City of Akko, Israel, renowned for its arcaded courtyard and distinctive granite columns.
-
C.
Khan al-Khayyatin
Khan al-Khayyatin is a historic caravanserai and traditional marketplace in Tripoli, Lebanon, known for its tailors and textile shops.
-
D.
Khan al-Sultan
Khan al-Sultan is a historic caravanserai and commercial complex located in the Muslim Quarter of Jerusalem’s Old City.
-
E.
Khan al-Gumruk
Khan al-Gumruk is a historic Ottoman-era caravanserai and commercial inn located within the old city of Aleppo, Syria.
- 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_69d6ada270808190b1a2b2e7b02bb426 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94da2a3cc81908de5a85257627fe2 |
completed | April 10, 2026, 7:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6556aae84819083e4988ec6f21471 |
completed | May 2, 2026, 7:50 p.m. |
Created at: April 8, 2026, 9:56 p.m.