Triple
T16647729
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karl Hajos |
E404515
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Karl Hajos |
E404515
|
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: Karl Hajos | Statement: [Karl Hajos, name, Karl Hajos]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Karl Hajos Context triple: [Karl Hajos, name, Karl Hajos]
-
A.
Karl Hajos
chosen
Karl Hajos was a Hungarian-American composer best known for his film scores during the early sound era of Hollywood cinema.
-
B.
Alfréd Hajós
Alfréd Hajós was a Hungarian swimmer and architect who became one of the first modern Olympic champions by winning multiple gold medals at the inaugural 1896 Games.
-
C.
Karl Wien
Karl Wien was a German mountaineer known for leading early high-altitude expeditions in Central Asia, including the pioneering ascent of Lenin Peak.
-
D.
Ödön Lechner
Ödön Lechner was a pioneering Hungarian architect often called the “Hungarian Gaudí,” renowned for fusing Art Nouveau forms with national folk motifs to create a distinctively Hungarian Secession style.
-
E.
Laszlo Molnar
Laszlo Molnar is a software developer and author known for creating the UPX (Ultimate Packer for Executables) executable compression tool.
- 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_69d8838a41f08190b0c3f79c47df5078 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37ad66fe88190be582b81719f2ac1 |
completed | April 18, 2026, 12:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00a50edea48190b65f4e6a9eb3ba24 |
completed | May 10, 2026, 3:32 p.m. |
Created at: April 10, 2026, 5:18 a.m.