Triple
T13332200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Theobald of Bec |
E317600
|
entity |
| Predicate | educatedAt |
P5
|
FINISHED |
| Object | Bec Abbey |
E835267
|
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: Bec Abbey | Statement: [Theobald of Bec, educatedAt, Bec Abbey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bec Abbey Context triple: [Theobald of Bec, educatedAt, Bec Abbey]
-
A.
Bec Abbey
chosen
Bec Abbey is a historic Benedictine monastery in Normandy, France, renowned as a major medieval center of learning and theology.
-
B.
Werden Abbey
Werden Abbey is a former Benedictine monastery in present-day Essen, Germany, historically significant as a religious and cultural center of the early Middle Ages.
-
C.
Cymer Abbey
Cymer Abbey is a ruined 12th-century Cistercian monastery in Gwynedd, Wales, noted for its picturesque setting near Dolgellau.
-
D.
Fore Abbey
Fore Abbey is a historic ruined Benedictine monastery in Ireland renowned for its early Christian heritage and the legendary “Seven Wonders of Fore.”
-
E.
Torre Abbey
Torre Abbey is a historic medieval monastery-turned-country house and art gallery in Torquay, Devon, known as one of the best-preserved monastic sites in southwest England.
- 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_69d806b4d62c81908d4ced1665414be5 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d9992fffa0819086610ae3bed2e2f9 |
completed | April 11, 2026, 12:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7266f70088190a518e273af507361 |
completed | May 3, 2026, 10:41 a.m. |
Created at: April 9, 2026, 9:30 p.m.