Triple
T14941030
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maritsa Peak |
E372525
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Musala |
E31301
|
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: Musala | Statement: [Maritsa Peak, locatedNear, Musala]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Musala Context triple: [Maritsa Peak, locatedNear, Musala]
-
A.
Musala
chosen
Musala is the highest mountain peak in the Balkans, located in the Rila Mountain range of southwestern Bulgaria.
-
B.
Mount Korab
Mount Korab is a prominent peak in the Balkan Peninsula that straddles the border between Albania and North Macedonia and is renowned for its rugged alpine terrain and scenic hiking routes.
-
C.
Falakro Mountain
Falakro Mountain is a prominent peak in northeastern Greece known for its ski resort and rugged natural landscapes.
-
D.
Mount Sipylus
Mount Sipylus is an ancient mountain in western Turkey traditionally associated with Greek myth, especially the story of Niobe’s transformation into stone.
-
E.
Mount Tzoumerka
Mount Tzoumerka is a rugged, high-altitude mountain massif in northwestern Greece known for its dramatic gorges, traditional stone villages, and rich natural landscapes within the Pindus range.
- 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_69d85cc9da0c81908d583ca3f63a3908 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded64a2f24819099b21566756668a2 |
completed | April 15, 2026, 12:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe7e929f3881908560b8428e72327d |
completed | May 9, 2026, 12:23 a.m. |
Created at: April 10, 2026, 2:38 a.m.