Triple
T9953104
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lubart |
E195376
|
entity |
| Predicate | languageOfChancery |
P30358
|
FINISHED |
| Object | Ruthenian |
—
|
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: Ruthenian | Statement: [Lubart, languageOfChancery, Ruthenian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfChancery Context triple: [Lubart, languageOfChancery, Ruthenian]
-
A.
hasChancery
Indicates that an entity possesses or is associated with a chancery, i.e., an official office or administrative body responsible for formal documents and records.
-
B.
languageOfPromulgation
Indicates the language in which a law, decree, or official act is formally issued or proclaimed.
-
C.
languageOfHistoricalRecord
chosen
Indicates the language in which a given historical record is written or recorded.
-
D.
lordChancellor
Indicates that one entity holds the position or role of Lord Chancellor in relation to another entity (such as a state, monarch, or government).
-
E.
languageOfOriginalPromulgation
Indicates the language in which a law, regulation, or official text was originally formally issued or published.
- 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_69ca82eaaa008190a54fa1a9f954b9ad |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb693918081908e9f96ef302235ad |
completed | April 2, 2026, 12:21 a.m. |
| PD | Predicate disambiguation | batch_69cd1d97c44081908730071269f07712 |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:46 p.m.