Triple
T3007569
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Church of All Nations |
E81938
|
entity |
| Predicate | predecessorOnSite |
P2283
|
FINISHED |
| Object | Byzantine church |
—
|
LITERAL 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: Byzantine church | Statement: [Church of All Nations, predecessorOnSite, Byzantine church]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: predecessorOnSite Context triple: [Church of All Nations, predecessorOnSite, Byzantine church]
-
A.
predecessorLocatedAt
chosen
Indicates that the location specified was the place where the immediately preceding version, state, or instance of an entity was situated.
-
B.
predecessor
Indicates that one entity comes before another in an ordered sequence or succession.
-
C.
predecessorInRole
Indicates that one entity previously held a particular role or position that was later occupied by another entity.
-
D.
predecessorState
Indicates that one state directly precedes another in a sequence or process.
-
E.
predecessorUser
Indicates that one user previously held a role, position, or state that is now held by another user, making the first user the predecessor of the second.
- F. None of above.
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_69ad8b1c4de88190a83b7cefaa1f2842 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9a4a12508190a48ae1c86233d25e |
completed | March 8, 2026, 3:48 p.m. |
| PD | Predicate disambiguation | batch_69ad96180eb08190a524c5f458d41382 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3 p.m.