Triple
T13561584
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tbilisi funicular |
E323920
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object | Mtatsminda slope |
E83047
|
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: Mtatsminda slope | Statement: [Tbilisi funicular, locatedOn, Mtatsminda slope]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mtatsminda slope Context triple: [Tbilisi funicular, locatedOn, Mtatsminda slope]
-
A.
Mount Mtatsminda
chosen
Mount Mtatsminda is a prominent mountain overlooking Tbilisi, Georgia, known for its panoramic views, historic sites, and cultural landmarks.
-
B.
Muizenberg Mountain
Muizenberg Mountain is a prominent peak forming part of the Cape Peninsula’s mountainous backdrop above the seaside suburb of Muizenberg in Cape Town, South Africa.
-
C.
Magaliesberg
Magaliesberg is a mountain range in northern South Africa known for its rugged cliffs, rich biodiversity, and historical significance in early Boer and indigenous history.
-
D.
Lovers Peak
"Lovers Peak" is a song featured on the album "Gravitas."
-
E.
Simonsberg
Simonsberg is a prominent mountain in South Africa’s Western Cape, known for its dramatic cliffs and surrounding wine-producing valleys near Stellenbosch.
- 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_69d8076830b48190910a902bae5888e2 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbaff5219081909cf60423e79d278f |
completed | April 12, 2026, 2:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f76bb1ef508190ab587bd2aa34795b |
completed | May 3, 2026, 3:37 p.m. |
Created at: April 9, 2026, 9:47 p.m.