Triple
T19406266
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Loch Goil |
E485469
|
entity |
| Predicate | hasNearbyMountain |
P651
|
FINISHED |
| Object | Ben Donich |
—
|
NE NERFINISHED |
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: Ben Donich | Statement: [Loch Goil, hasNearbyMountain, Ben Donich]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ben Donich Context triple: [Loch Goil, hasNearbyMountain, Ben Donich]
-
A.
Ben Donich
chosen
Ben Donich is a mountain in the Arrochar Alps of the Scottish Highlands, popular with hikers for its accessible ascent and panoramic views.
-
B.
Jason Bittner
Jason Bittner is an American heavy metal drummer best known for his work with the band Shadows Fall and his highly technical, influential playing style.
-
C.
Ben Kutchins
Ben Kutchins is an American cinematographer known for his work on both film and television, including acclaimed series such as "Ozark."
-
D.
Steven Bethard
Steven Bethard is a computer scientist and natural language processing researcher known for his work on temporal information extraction, semantic role labeling, and clinical NLP.
-
E.
Christopher Jahnke
Christopher Jahnke is an American musical theatre orchestrator known for his work on numerous Broadway productions.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8d5162481909db12435d9535c1a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6257af68881908147beedc29ff64c |
completed | April 20, 2026, 1:09 p.m. |
Created at: April 10, 2026, 1:36 p.m.