Triple
T14521420
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Falcon Souq |
E340658
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Souq Waqif |
E68114
|
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: Souq Waqif | Statement: [Falcon Souq, near, Souq Waqif]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Souq Waqif Context triple: [Falcon Souq, near, Souq Waqif]
-
A.
Souq Waqif
chosen
Souq Waqif is a historic traditional market in Doha, Qatar, known for its restored Qatari architecture, bustling alleys of shops and restaurants, and vibrant cultural atmosphere.
-
B.
Souq Al-Mubarakiya
Souq Al-Mubarakiya is one of Kuwait’s oldest traditional markets, known for its historic architecture, local foods, spices, textiles, and vibrant cultural atmosphere.
-
C.
Al-Madina Souq
Al-Madina Souq is a historic covered market in Aleppo, Syria, renowned as one of the largest and oldest traditional bazaars in the Middle East.
-
D.
Souq Al Majarrah
Souq Al Majarrah was a traditional waterfront market building in Sharjah that was later converted into the Sharjah Museum of Islamic Civilization.
-
E.
Muttrah Souq
Muttrah Souq is a historic, maze-like traditional market in Muscat, Oman, renowned for its bustling atmosphere and stalls selling spices, textiles, jewelry, and handicrafts.
- 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_69d822dac79c8190a84a073f3cbaced5 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69de9a72cff08190878b4bed9b0b5eb5 |
completed | April 14, 2026, 7:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd8ab07e08819085a6a21cc9cea1fa |
completed | May 8, 2026, 7:03 a.m. |
Created at: April 10, 2026, 1:22 a.m.