Triple
T742347
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dead Sea |
E15269
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Ein Gedi |
E61475
|
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: Ein Gedi | Statement: [Dead Sea, near, Ein Gedi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ein Gedi Context triple: [Dead Sea, near, Ein Gedi]
-
A.
Ein Gedi
chosen
Ein Gedi is an oasis and nature reserve in the Judean Desert of Israel, famed for its springs, waterfalls, rich wildlife, and archaeological sites.
-
B.
Bir el Gubi
Bir el Gubi was a strategically important desert battlefield in Libya during World War II, known for significant clashes between British Commonwealth and Italian-German forces.
-
C.
Masada
Masada is an ancient desert fortress in Israel, famed as the site of the Jewish rebels’ last stand against the Romans and now a major archaeological and UNESCO World Heritage site.
-
D.
Wadi Rum
Wadi Rum is a vast desert valley in southern Jordan known for its dramatic sandstone mountains, red sand dunes, and use as a filming location for Mars-like landscapes.
-
E.
Marḥeshvan
Marḥeshvan is the eighth month of the Hebrew calendar, traditionally noted for having no major Jewish holidays.
- 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_69a49358aa308190adbc9b5a0a2adcf9 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a60e286c81908787a41cf9b9f150 |
completed | March 1, 2026, 8:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a673345f18819084e2caf380e46b30 |
completed | March 3, 2026, 5:35 a.m. |
Created at: March 1, 2026, 7:37 p.m.