Triple
T22669141
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ivan Broz |
E559873
|
entity |
| Predicate | hasFamilyName |
P18
|
FINISHED |
| Object | Broz |
—
|
NE NERFINISHED |
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: Broz | Statement: [Ivan Broz, hasFamilyName, Broz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Broz Context triple: [Ivan Broz, hasFamilyName, Broz]
-
A.
Broz
chosen
Broz is a surname most famously associated with Josip Broz Tito, the former president of Yugoslavia, and his wife Jovanka Broz.
-
B.
Bronek
Bronek is a Polish diminutive given name commonly used as a familiar or affectionate form of Bronisław.
-
C.
Buzek
Buzek is a Polish surname most notably associated with Jerzy Buzek, a former Prime Minister of Poland and President of the European Parliament.
-
D.
Brod
Brod is a surname most notably associated with Max Brod, the Czech-born German-language writer, composer, and friend and editor of Franz Kafka.
-
E.
Ambroz
Ambroz is a river in Spain that serves as a tributary of the Alagón River.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2454a158c819093b8e35f5045efb6 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1781de1d48190947cb1bb9d0890d9 |
completed | April 29, 2026, 3:16 a.m. |
Created at: April 17, 2026, 3:09 p.m.