Triple
T10676630
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gregorios |
E251635
|
entity |
| Predicate | hasCognate |
P2525
|
FINISHED |
| Object | Gregorius |
E620698
|
NE 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: Gregorius | Statement: [Gregorios, hasCognate, Gregorius]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gregorius Context triple: [Gregorios, hasCognate, Gregorius]
-
A.
Gregorius
chosen
Gregorius was a Roman jurist traditionally credited with compiling the Codex Gregorianus, one of the earliest systematic collections of imperial legal constitutions.
-
B.
Juhanus
Juhanus is a variant form of the Estonian male given name Jaan, itself equivalent to John.
-
C.
Laurentius
Laurentius is a Latin given name historically borne by several early Christian saints and later adapted into various European forms such as Laurence and Lawrence.
-
D.
Franciscus
Franciscus is the Latinized given name of the renowned Dutch primatologist and ethologist Frans de Waal.
-
E.
Marianus
Marianus is a Latin personal name, historically used in the Roman world and later in various European cultures, derived from the root name Marian.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6aa5b0d2881909584b20efc5877f0 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6fb94b05c8190b66bf64f5c6d166b |
completed | April 9, 2026, 1:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d98876222c8190be638bdfa3ce4ceb |
completed | April 10, 2026, 11:32 p.m. |
Created at: April 8, 2026, 9:09 p.m.