Triple
T18295152
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pernaja |
E438210
|
entity |
| Predicate | hasNotableChurch |
P15000
|
FINISHED |
| Object |
Pernaja Church
Pernaja Church is a historic medieval stone church in Pernaja, Finland, known for its traditional architecture and cultural significance in the region.
|
E1316553
|
NE FINISHED |
How this triple was built (4 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: Pernaja Church | Statement: [Pernaja, hasNotableChurch, Pernaja Church]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pernaja Church Context triple: [Pernaja, hasNotableChurch, Pernaja Church]
-
A.
Paxton Church
Paxton Church is a Christian place of worship serving the local community of Paxton.
-
B.
Etne Church
Etne Church is a historic parish church of the Church of Norway located in the village of Etne in western Norway.
-
C.
Phillips Church
Phillips Church is a historic chapel located on the campus of Phillips Exeter Academy in Exeter, New Hampshire, serving as a center for the school's religious and community gatherings.
-
D.
Wainee Church
Wainee Church is the original historic name of Waiola Church, one of Hawaii’s oldest Christian congregations located in Lahaina, Maui.
-
E.
Prentiss Church
Prentiss Church is a hip-hop artist best known for his work and collaborations within Nelly’s Derrty Entertainment collective.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Pernaja Church Triple: [Pernaja, hasNotableChurch, Pernaja Church]
Generated description
Pernaja Church is a historic medieval stone church in Pernaja, Finland, known for its traditional architecture and cultural significance in the region.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Pernaja Church Target entity description: Pernaja Church is a historic medieval stone church in Pernaja, Finland, known for its traditional architecture and cultural significance in the region.
-
A.
Paxton Church
Paxton Church is a Christian place of worship serving the local community of Paxton.
-
B.
Etne Church
Etne Church is a historic parish church of the Church of Norway located in the village of Etne in western Norway.
-
C.
Phillips Church
Phillips Church is a historic chapel located on the campus of Phillips Exeter Academy in Exeter, New Hampshire, serving as a center for the school's religious and community gatherings.
-
D.
Wainee Church
Wainee Church is the original historic name of Waiola Church, one of Hawaii’s oldest Christian congregations located in Lahaina, Maui.
-
E.
Prentiss Church
Prentiss Church is a hip-hop artist best known for his work and collaborations within Nelly’s Derrty Entertainment collective.
- F. None of above. chosen
Provenance (5 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_69d8b915e3e881909125d760c15d0c29 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e5017783748190905ce4eeadd25841 |
completed | April 19, 2026, 4:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a03bb5a98808190ae1bbb9a4f11b96d |
completed | May 12, 2026, 11:44 p.m. |
| NEDg | Description generation | batch_6a03bc1a53448190b97e10027fd1347f |
completed | May 12, 2026, 11:47 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a03bca3286c819091db45df95d855e4 |
completed | May 12, 2026, 11:49 p.m. |
Created at: April 10, 2026, 10:35 a.m.