Triple
T11881245
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Glyderau |
E282662
|
entity |
| Predicate | separatedFrom |
P243
|
FINISHED |
| Object | Snowdon Massif |
E322722
|
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: Snowdon Massif | Statement: [Glyderau, separatedFrom, Snowdon Massif]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Snowdon Massif Context triple: [Glyderau, separatedFrom, Snowdon Massif]
-
A.
Snowdon Massif
chosen
Snowdon Massif is the central mountainous group in Snowdonia, Wales, encompassing Snowdon and its surrounding peaks and ridges.
-
B.
Snowdonia
Snowdonia is a mountainous region and national park in northwest Wales, renowned for its rugged landscapes, lakes, and the highest peak in Wales, Mount Snowdon.
-
C.
Snowdon
Snowdon is the tallest and most famous mountain in Wales, renowned for its scenic hiking routes and panoramic views.
-
D.
Snowdon
Snowdon is a major Montreal Metro station in the Côte-des-Neiges–Notre-Dame-de-Grâce borough that serves as an important transfer point between multiple subway lines.
-
E.
Carnedd Llywelyn
Carnedd Llywelyn is a prominent mountain in Snowdonia, Wales, known as one of the highest peaks in the country and a major summit of the Carneddau 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_69d6ab2945d081908a5851c916cbcfb5 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8d39d2934819093b9f7006f45e5cb |
completed | April 10, 2026, 10:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f43fd661f481909b1f7609540e42d7 |
completed | May 1, 2026, 5:53 a.m. |
Created at: April 8, 2026, 9:44 p.m.