Triple
T7161674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Scarinish |
E166958
|
entity |
| Predicate | hasNearbyIsland |
P970
|
FINISHED |
| Object | Coll |
E15004
|
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: Coll | Statement: [Scarinish, hasNearbyIsland, Coll]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Coll Context triple: [Scarinish, hasNearbyIsland, Coll]
-
A.
Coll
chosen
Coll is a small, sparsely populated island in the Inner Hebrides of Scotland, known for its sandy beaches, dark skies, and rich wildlife.
-
B.
Cor
Cor is a common Dutch diminutive or short form of the given name Cornelis.
-
C.
Cam
Cam is the given name of Cam Neely, a former professional ice hockey player and current president of the Boston Bruins.
-
D.
Kollidam
Kollidam is a major distributary of the Kaveri River in Tamil Nadu, India, flowing past Srirangam and playing an important role in the region’s irrigation and riverine landscape.
-
E.
Kon
Kon is a deity from Andean mythology often associated with rain, wind, and the fertilizing forces that sustain life in the region.
- 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_69c68887a5cc8190bec0ea96227164f7 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e82e4b248190ad3c3863cb93971e |
completed | March 27, 2026, 8:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7adc4b7648190969fab0351f9fd22 |
completed | March 28, 2026, 10:30 a.m. |
Created at: March 27, 2026, 2:47 p.m.