Triple
T15485346
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marsa Alam |
E377031
|
entity |
| Predicate | nearestMajorCity |
P1982
|
FINISHED |
| Object | Luxor |
E16540
|
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: Luxor | Statement: [Marsa Alam, nearestMajorCity, Luxor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Luxor Context triple: [Marsa Alam, nearestMajorCity, Luxor]
-
A.
Luxor
chosen
Luxor is a historic city in southern Egypt renowned for its vast ancient temple complexes and royal tombs along the Nile.
-
B.
Helwan
Helwan is an industrial and residential city in southern Greater Cairo, Egypt, known for its factories, universities, and historic spa resorts along the Nile.
-
C.
Shebin El Qanater
Shebin El Qanater is a city in Egypt’s Qalyubia Governorate, located in the Nile Delta north of Cairo.
-
D.
Abu Simbel town
Abu Simbel town is a small settlement in southern Egypt best known as the modern community serving visitors to the famous rock-cut Abu Simbel temples near the Sudanese border.
-
E.
Edfu
Edfu is an ancient Egyptian city best known for its remarkably well-preserved Ptolemaic temple dedicated to the falcon god Horus.
- 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_69d85cd21dcc81908646251b1c26ea00 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03f8f71a08190a440ff19dcc65312 |
completed | April 16, 2026, 1:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff2d1170088190a911f8ea8d2a2066 |
completed | May 9, 2026, 12:48 p.m. |
Created at: April 10, 2026, 3:46 a.m.