Triple
T21844001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seljuk Rum period |
E539326
|
entity |
| Predicate | hasPrecedingEntity |
P11018
|
FINISHED |
| Object | Byzantine rule in Anatolia |
—
|
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 rule in Anatolia | Statement: [Seljuk Rum period, hasPrecedingEntity, Byzantine rule in Anatolia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrecedingEntity Context triple: [Seljuk Rum period, hasPrecedingEntity, Byzantine rule in Anatolia]
-
A.
hasPrecedingCondition
Indicates that one condition occurs or exists before another condition in time or sequence.
-
B.
hasPrecedingEvents
chosen
Indicates that one or more events occurred earlier in time or sequence relative to the referenced event.
-
C.
hasPrecedingWork
Indicates that one work comes before another in a sequence, serving as its predecessor.
-
D.
precededByDocument
Indicates that one document occurs or is issued earlier in sequence or time than another document.
-
E.
hasPredecessorMP
Indicates that one member of parliament previously held the same parliamentary position or seat before another member of parliament.
- 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_69e0c476c3c88190a92d08ebb59a128a |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f0bd5248f08190ba208512eafbe7ad |
completed | April 28, 2026, 1:59 p.m. |
| PD | Predicate disambiguation | batch_69e6be8c14748190bdcc44a14d50bea4 |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 6:55 p.m.