Triple
T6215537
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ikhshidid dynasty |
E138977
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Fustat |
E141156
|
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: Fustat | Statement: [Ikhshidid dynasty, capital, Fustat]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fustat Context triple: [Ikhshidid dynasty, capital, Fustat]
-
A.
Fustat
chosen
Fustat was the early Islamic capital of Egypt and a major medieval urban center that later became part of Cairo.
-
B.
Fatimid Cairo
Fatimid Cairo was the medieval capital of the Fatimid Caliphate in Egypt, serving as a major political, religious, and cultural center of the Ismaili Shia Muslim world.
-
C.
Umm el-Qaab
Umm el-Qaab is an early dynastic royal cemetery at Abydos in Upper Egypt, known as the burial place of many of Egypt’s first pharaohs.
-
D.
Kasr Al Ainy
Kasr Al Ainy is a historic medical campus and hospital complex in Cairo that serves as the main site of Cairo University's Faculty of Medicine.
-
E.
Gemmayzeh
Gemmayzeh is a historic, bohemian neighborhood in Beirut known for its traditional architecture, vibrant nightlife, and cultural scene.
- 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_69c008aecb0c81909984b48f733ce8ae |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c062a0e0488190b71b42386bacf982 |
completed | March 22, 2026, 9:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c243e998e0819090a2162e2a0ab7b9 |
completed | March 24, 2026, 7:57 a.m. |
Created at: March 22, 2026, 4:21 p.m.