Triple
T21893247
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Glangevlin |
E540606
|
entity |
| Predicate | nearbySettlement |
P350
|
FINISHED |
| Object | Blacklion |
—
|
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: Blacklion | Statement: [Glangevlin, nearbySettlement, Blacklion]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Blacklion Context triple: [Glangevlin, nearbySettlement, Blacklion]
-
A.
Blacklion
chosen
Blacklion is a small village in County Cavan, Ireland, situated close to the Cuilcagh Mountain region and known as a gateway to the surrounding lakelands and karst landscapes.
-
B.
Lion-Mher
Lion-Mher is a heroic figure from the Armenian epic cycle "Daredevils of Sassoun," renowned for his extraordinary strength and lion-like bravery.
-
C.
Manticore
Manticore is a covert, high-tech paramilitary organization in the Dark Angel universe that engineers and controls genetically enhanced super-soldiers.
-
D.
Keleos
Keleos is a figure from Greek mythology, known as the king of Eleusis who hosted the goddess Demeter during her search for Persephone.
-
E.
Black Lion
Black Lion is a historic pub in London whose name inspired the nearby Black Lion Gate.
- 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_69e0c47a95908190ae3e19b716accb3d |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f11fc46dd481908a119cfbe26564a3 |
completed | April 28, 2026, 8:59 p.m. |
Created at: April 16, 2026, 7:07 p.m.