Triple
T3948837
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Daphni Monastery |
E84812
|
entity |
| Predicate | patronDuringRebuilding |
P53068
|
FINISHED |
| Object | Byzantine aristocracy |
—
|
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 aristocracy | Statement: [Daphni Monastery, patronDuringRebuilding, Byzantine aristocracy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: patronDuringRebuilding Context triple: [Daphni Monastery, patronDuringRebuilding, Byzantine aristocracy]
-
A.
rebuildPeriod
Indicates the time span during which something is reconstructed or restored after damage, failure, or decommissioning.
-
B.
reconstructedDuring
Indicates that an entity was rebuilt, restored, or significantly repaired within a specified time period or event.
-
C.
reopenedAfterReconstruction
Indicates that a place or facility resumed operations after undergoing reconstruction or major rebuilding work.
-
D.
notRebuiltAfter
Indicates that an entity was destroyed or damaged and has not been reconstructed or restored after a specified event or point in time.
-
E.
rebuiltOn
Indicates that one entity has been reconstructed, restored, or built again on, over, or using the foundation, structure, or basis of another entity.
- F. None of above. chosen
Provenance (4 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_69aed934fbfc8190847068e4546de963 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefaa5afdc8190b709af2473d75d02 |
completed | March 9, 2026, 4:51 p.m. |
| PD | Predicate disambiguation | batch_69aef8ed04e4819096bced8971cd888d |
completed | March 9, 2026, 4:44 p.m. |
| PDg | Predicate description generation | batch_69aefaa3c6a08190bfe76629c7c98eea |
completed | March 9, 2026, 4:51 p.m. |
Created at: March 9, 2026, 3:30 p.m.