Triple
T28496841
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Akdamar Island |
E721127
|
entity |
| Predicate | mainChurchArchitect |
P138
|
FINISHED |
| Object |
Manuel (architect)
Manuel was a medieval Armenian architect best known for designing the famed Holy Cross Church on Akdamar Island in Lake Van.
|
E1820790
|
NE FINISHED |
How this triple was built (3 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: Manuel (architect) | Statement: [Akdamar Island, mainChurchArchitect, Manuel (architect)]
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: Manuel (architect) Triple: [Akdamar Island, mainChurchArchitect, Manuel (architect)]
Generated description
Manuel was a medieval Armenian architect best known for designing the famed Holy Cross Church on Akdamar Island in Lake Van.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainChurchArchitect Context triple: [Akdamar Island, mainChurchArchitect, Manuel (architect)]
-
A.
originalChurchArchitect
Indicates that one entity is the architect who originally designed the church represented by the other entity.
-
B.
coArchitectOf
Indicates a relationship where two or more entities jointly serve as architects of the same project, design, or structure.
-
C.
originalChurchBuiltBy
Indicates that a particular original church was constructed or established through the actions, direction, or initiative of a specified agent or entity.
-
D.
architectOfMainBuilding
chosen
Indicates that one entity is the architect who designed the main building associated with another entity.
-
E.
cathedralDesignedBy
Indicates that a specific cathedral was designed or planned by a particular architect or designer.
- F. None of above.
Provenance (6 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_69f01a5afdac8190ac6e72d5c100bd58 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f6f8565134819096aac0175f924a9f |
completed | May 3, 2026, 7:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a1641a99f10819088c373073720a731 |
completed | May 27, 2026, 12:58 a.m. |
| NEDg | Description generation | batch_6a164228e3ac8190a1574562a734b13f |
completed | May 27, 2026, 1 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a164611b60c819083a14fcba602a299 |
completed | May 27, 2026, 1:17 a.m. |
| PD | Predicate disambiguation | batch_69f6f65fd1d08190b88e5e68ba268500 |
completed | May 3, 2026, 7:16 a.m. |
Created at: April 28, 2026, 3:04 a.m.