Triple
T16351597
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tusheti |
E397072
|
entity |
| Predicate | hasPass |
P11208
|
FINISHED |
| Object | Abano Pass |
E1176674
|
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: Abano Pass | Statement: [Tusheti, hasPass, Abano Pass]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Abano Pass Context triple: [Tusheti, hasPass, Abano Pass]
-
A.
Abano Pass
chosen
Abano Pass is a high-altitude mountain pass in Georgia that connects the remote Tusheti region with the rest of the country and is known for its steep, rugged terrain and seasonal accessibility.
-
B.
Mortirolo Pass
Mortirolo Pass is a steep and legendary mountain pass in the Italian Alps, renowned as one of the toughest climbs in professional road cycling.
-
C.
Sella Pass
Sella Pass is a high mountain pass in the Dolomites of northern Italy, renowned for its dramatic alpine scenery and popularity with hikers, climbers, and cyclists.
-
D.
Campolongo Pass
Campolongo Pass is a high mountain pass in the Dolomites of northern Italy, linking the valleys of Corvara and Arabba and serving as a popular route for cyclists and skiers.
-
E.
Passo Gavia
Passo Gavia is a high mountain pass in the Italian Alps renowned among cyclists for its challenging gradients and frequent inclusion in major professional races.
- 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_69d87f26864c819088365ca381a003c2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2facbf60c8190aa47d4c45ff59354 |
completed | April 18, 2026, 3:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a002db6375c81908c64dbe2bc987b1a |
completed | May 10, 2026, 7:03 a.m. |
Created at: April 10, 2026, 5:07 a.m.