Triple
T738166
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erling-Andechs |
E14980
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Andechs Abbey |
E90654
|
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: Andechs Abbey | Statement: [Erling-Andechs, hasLandmark, Andechs Abbey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andechs Abbey Context triple: [Erling-Andechs, hasLandmark, Andechs Abbey]
-
A.
Andechs Abbey
chosen
Andechs Abbey is a Benedictine monastery in Bavaria, Germany, renowned as a major pilgrimage site and for its historic brewery and scenic hilltop setting above the Ammersee.
-
B.
Klosterlangheim
Klosterlangheim is a village and former monastery site that is now a district of the town of Lichtenfels in Bavaria, Germany.
-
C.
Fossanova Abbey
Fossanova Abbey is a medieval Cistercian monastery in Italy, renowned as the place where the theologian and philosopher St. Thomas Aquinas died.
-
D.
Wartburg Castle
Wartburg Castle is a medieval fortress in Eisenach, Germany, famed as the place where Martin Luther translated the New Testament into German while in hiding.
-
E.
Ulm Minster
Ulm Minster is a famous Gothic church in Ulm, Germany, renowned for having the tallest church steeple in the world.
- 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_69a4934d9930819099eed80096b0597d |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a5f1c9888190b2817138c6893cfe |
completed | March 1, 2026, 8:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a673329a0c8190b725b9863ba4c162 |
completed | March 3, 2026, 5:35 a.m. |
Created at: March 1, 2026, 7:37 p.m.