Triple
T18680775
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sameba |
E456726
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object | Sameba Cathedral |
—
|
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: Sameba Cathedral | Statement: [Sameba, shortName, Sameba Cathedral]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sameba Cathedral Context triple: [Sameba, shortName, Sameba Cathedral]
-
A.
Sameba Cathedral
chosen
Sameba Cathedral is a monumental Georgian Orthodox cathedral in Tbilisi and one of the largest religious buildings in the Caucasus.
-
B.
Dili Cathedral
Dili Cathedral is the main Roman Catholic cathedral and one of the most prominent religious and cultural landmarks in the capital city of Timor-Leste.
-
C.
Passu Cathedral
Passu Cathedral is a striking group of sharply pointed mountain peaks in the Hunza Valley of northern Pakistan, renowned for their dramatic, cathedral-like spires.
-
D.
Bata Cathedral
Bata Cathedral is a prominent Roman Catholic church and architectural landmark located in the coastal city of Bata in Equatorial Guinea.
-
E.
Lipa Cathedral
Lipa Cathedral is a prominent Roman Catholic cathedral and historical landmark located in Lipa City, Batangas, Philippines.
- 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_69d8d391eb488190ac2e9abf5bf255e4 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e55b2840548190ababe1cc603b4784 |
completed | April 19, 2026, 10:46 p.m. |
Created at: April 10, 2026, 11:48 a.m.