Triple
T3213387
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Morgan le Fay |
E67333
|
entity |
| Predicate | associatedPlace |
P1481
|
FINISHED |
| Object | Avalon |
E195682
|
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: Avalon | Statement: [Morgan le Fay, associatedPlace, Avalon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Avalon Context triple: [Morgan le Fay, associatedPlace, Avalon]
-
A.
Avalon
Avalon is a federal electoral district in Newfoundland and Labrador, Canada, represented in the House of Commons.
-
B.
Avalon
chosen
Avalon is the legendary, mystical island in Arthurian mythology famed as the place of King Arthur’s healing or final rest and the forging of Excalibur.
-
C.
Dunoon
Dunoon is a coastal town and former resort on the Cowal peninsula in Argyll and Bute, western Scotland.
-
D.
Avallon
Avallon is a historic commune in central France known for its medieval architecture and scenic location on a granite outcrop in the Burgundy region.
-
E.
Caere
Caere was a major ancient Etruscan city-state in central Italy, noted for its wealth, maritime trade, and close cultural contacts with the Greek and Phoenician worlds.
- 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_69ad858ac36c81909962589cd277d6e2 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaabba8e481909118d9f888ddcd63 |
completed | March 8, 2026, 4:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b26237211c81908cddc4e8d42e497e |
completed | March 12, 2026, 6:50 a.m. |
Created at: March 8, 2026, 3:07 p.m.