Triple
T2067657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hamish |
E45939
|
entity |
| Predicate | hasCognate |
P2525
|
FINISHED |
| Object | Jakub |
E49733
|
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: Jakub | Statement: [Hamish, hasCognate, Jakub]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jakub Context triple: [Hamish, hasCognate, Jakub]
-
A.
Jakub
chosen
Jakub is a given name, common in Slavic countries, that is a cognate of the Latin name Iacomus (James).
-
B.
Michal
Michal is a biblical figure, a daughter of King Saul who became the first wife of King David in the Hebrew Bible.
-
C.
Jozef
Jozef is a masculine given name of Hebrew origin, commonly used in Central and Eastern Europe as a variant of Joseph.
-
D.
Karol
Karol is the given name of Pope John Paul II, the Polish-born head of the Catholic Church from 1978 to 2005.
-
E.
Janek
Janek is the gruff but good-natured captain of the spaceship Prometheus in Ridley Scott’s 2012 science fiction film.
- 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_69a8891b38288190abd572ccad9b6928 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb9f362f48190b1b0e560424c3aef |
completed | March 7, 2026, 5:38 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae305263f88190b448fb134163d5aa |
completed | March 9, 2026, 2:28 a.m. |
Created at: March 4, 2026, 7:40 p.m.