Triple
T12415588
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ivan Shishman |
E296626
|
entity |
| Predicate | realmFragmentation |
P46959
|
FINISHED |
| Object | division between Tarnovo and Vidin tsardoms |
—
|
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: division between Tarnovo and Vidin tsardoms | Statement: [Ivan Shishman, realmFragmentation, division between Tarnovo and Vidin tsardoms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: realmFragmentation Context triple: [Ivan Shishman, realmFragmentation, division between Tarnovo and Vidin tsardoms]
-
A.
fragmentationLevel
Indicates the degree to which something is broken into smaller, separate parts or segments.
-
B.
successorStateFragmentation
chosen
Indicates that a successor state experiences division or breakup into multiple smaller political or administrative units.
-
C.
divisionSince
Indicates that one entity has been divided or split from another starting at a specific point in time.
-
D.
divisionFrequency
Indicates how often a division event occurs within a given context or time frame.
-
E.
realm
Indicates that one entity is a domain, sphere of influence, or area of control associated with another entity.
- 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_69d6ad9f464c81909db36d7e96e34b9e |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94e1888b48190bd750f839a26e99e |
completed | April 10, 2026, 7:23 p.m. |
| PD | Predicate disambiguation | batch_69d94d354b488190adc83fb4f2770dd5 |
completed | April 10, 2026, 7:19 p.m. |
Created at: April 8, 2026, 9:55 p.m.