Triple
T12641288
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tanis |
E301902
|
entity |
| Predicate | modernNearbySettlement |
P8489
|
FINISHED |
| Object | San el-Hagar |
E901540
|
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: San el-Hagar | Statement: [Tanis, modernNearbySettlement, San el-Hagar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: San el-Hagar Context triple: [Tanis, modernNearbySettlement, San el-Hagar]
-
A.
Sakhrah
Sakhrah is the Arabic name for the Foundation Stone, the sacred rock at the heart of Jerusalem’s Temple Mount and the Dome of the Rock.
-
B.
San al-Hagar al-Qibliyah
chosen
San al-Hagar al-Qibliyah is a town in Egypt’s Nile Delta region, located within the Sharqia Governorate.
-
C.
El Zawya El Hamra
El Zawya El Hamra is a residential district and urban neighborhood located in the northeastern part of Cairo, Egypt.
-
D.
Hammada
Hammada is a small genus of hardy, drought-tolerant shrubs native to arid and semi-arid regions, often found in desert and steppe ecosystems.
-
E.
Al Bani Hajar
Al Bani Hajar is an Arab subtribe belonging to the larger Qahtan tribal confederation, traditionally associated with southern Arabia.
- 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_69d7bdec9f9c8190b4bac675b7588211 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9614ae6ac8190b42acbf2b0331fda |
completed | April 10, 2026, 8:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6719a45d881908dd895836a225781 |
completed | May 2, 2026, 9:50 p.m. |
Created at: April 9, 2026, 5:17 p.m.