Triple
T7989154
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint Benedict Chapel |
E185757
|
entity |
| Predicate | location |
P40
|
FINISHED |
| Object | Sumvitg |
E185761
|
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: Sumvitg | Statement: [Saint Benedict Chapel, location, Sumvitg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sumvitg Context triple: [Saint Benedict Chapel, location, Sumvitg]
-
A.
Sumvitg
chosen
Sumvitg is a municipality in the Swiss canton of Graubünden, known for its alpine setting and contemporary chapel designed by architect Peter Zumthor.
-
B.
Kimvita
Kimvita is a major coastal dialect of Swahili spoken primarily in and around Mombasa, Kenya.
-
C.
Susitnu
Susitnu is the Indigenous (Dena’ina) name for Alaska’s Susitna River, a major waterway in south-central Alaska.
-
D.
Vitasta
Vitasta is the ancient Sanskrit name for the Jhelum River, a historically significant river of the Kashmir region frequently mentioned in Vedic and classical Indian texts.
-
E.
Shivta
Shivta is an ancient Nabatean and Byzantine desert city in Israel, known for its remarkably well-preserved ruins and role along historic trade routes.
- 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_69ca829a2cfc819083d591d58ec04075 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3c4f98808190879113ad4af9bb4d |
completed | March 31, 2026, 3:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cbe0ed61588190b01423061acfce49 |
completed | March 31, 2026, 2:57 p.m. |
Created at: March 30, 2026, 5:16 p.m.