Triple
T14451111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leopold Okulicki |
E358335
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Okulicki |
E358335
|
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: Okulicki | Statement: [Leopold Okulicki, familyName, Okulicki]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Okulicki Context triple: [Leopold Okulicki, familyName, Okulicki]
-
A.
Okulicki
chosen
Okulicki is the surname of Leopold Okulicki, the last commander of the Polish Home Army during World War II.
-
B.
Okulaja
Okulaja is a surname most notably associated with individuals of Nigerian or German-Nigerian heritage, including figures in sports and academia.
-
C.
Okulovka
Okulovka is a small town in western Russia known as a local administrative and railway hub within Novgorod Oblast.
-
D.
Askole
Askole is a remote high-altitude village in Pakistan’s Karakoram range that serves as a key gateway for trekking and mountaineering expeditions to major glaciers and peaks, including K2.
-
E.
Schull
Schull is a small coastal village and popular tourist destination on the Mizen Peninsula in West County Cork, Ireland.
- 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_69d82794dfa081909b9134ad2e32244b |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de916244948190bb09d1bfc485ba50 |
completed | April 14, 2026, 7:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd5be12da481909b11290965ec48da |
completed | May 8, 2026, 3:43 a.m. |
Created at: April 10, 2026, 1:19 a.m.