Triple
T21855501
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | As-Suwayda |
E539613
|
entity |
| Predicate | nearbyAncientSite |
P2064
|
FINISHED |
| Object | Salkhad |
—
|
NE NERFINISHED |
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: Salkhad | Statement: [As-Suwayda, nearbyAncientSite, Salkhad]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Salkhad Context triple: [As-Suwayda, nearbyAncientSite, Salkhad]
-
A.
Salkhad
chosen
Salkhad is a historic town in southern Syria known for its ancient fortress and its location within the predominantly Druze Jabal al-Druze region.
-
B.
Solkhat
Solkhat is the historical name of Stary Krym, an ancient town in Crimea that once served as an important medieval trade and administrative center.
-
C.
Khardaha
Khardaha is a suburban city in the Indian state of West Bengal, located near Kolkata along the Hooghly River and known as part of the Kolkata metropolitan area.
-
D.
Kharax
Kharax is a figure significant enough—likely a historical ruler, noble, or legendary personage—to have the Kharax Palace named in their honor.
-
E.
Jakharrah
Jakharrah is a settlement located in Libya’s Al Wahat District, an eastern region known for its desert landscapes and oases.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c47829648190bbe2d1d7033768ec |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f0d635b59c81908810480f3802b847 |
completed | April 28, 2026, 3:45 p.m. |
Created at: April 16, 2026, 6:56 p.m.