Triple
T19210674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ustream |
E480348
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object |
Gyula Fehér
Gyula Fehér is a technology entrepreneur best known as a co-founder of the live video streaming platform Ustream.
|
E1367060
|
NE FINISHED |
How this triple was built (4 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: Gyula Fehér | Statement: [Ustream, foundedBy, Gyula Fehér]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gyula Fehér Context triple: [Ustream, foundedBy, Gyula Fehér]
-
A.
Vilmos Gábor
Vilmos Gábor was the father of Hungarian-American actress and socialite Zsa Zsa Gabor.
-
B.
Ernő Gerő
Ernő Gerő was a hardline Hungarian communist leader and brief de facto head of state whose intransigent policies and actions helped trigger the 1956 Hungarian Revolution.
-
C.
János Feketeházy
János Feketeházy was a Hungarian engineer and architect best known for designing major 19th-century railway structures, including Budapest’s Keleti Railway Station.
-
D.
István Dobó
István Dobó was a 16th-century Hungarian military commander best known for leading the successful defense of Eger against the Ottoman siege in 1552.
-
E.
Gyula Jankovits
Gyula Jankovits was a Hungarian sculptor best known for creating prominent public monuments in Budapest, including the Gellért Monument.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Gyula Fehér Triple: [Ustream, foundedBy, Gyula Fehér]
Generated description
Gyula Fehér is a technology entrepreneur best known as a co-founder of the live video streaming platform Ustream.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Gyula Fehér Target entity description: Gyula Fehér is a technology entrepreneur best known as a co-founder of the live video streaming platform Ustream.
-
A.
Vilmos Gábor
Vilmos Gábor was the father of Hungarian-American actress and socialite Zsa Zsa Gabor.
-
B.
Ernő Gerő
Ernő Gerő was a hardline Hungarian communist leader and brief de facto head of state whose intransigent policies and actions helped trigger the 1956 Hungarian Revolution.
-
C.
János Feketeházy
János Feketeházy was a Hungarian engineer and architect best known for designing major 19th-century railway structures, including Budapest’s Keleti Railway Station.
-
D.
István Dobó
István Dobó was a 16th-century Hungarian military commander best known for leading the successful defense of Eger against the Ottoman siege in 1552.
-
E.
Gyula Jankovits
Gyula Jankovits was a Hungarian sculptor best known for creating prominent public monuments in Budapest, including the Gellért Monument.
- F. None of above. chosen
Provenance (5 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_69d8e8cb8c348190b52075823911c869 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fa365c2481909b3c36ebae18265d |
completed | April 20, 2026, 10:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a070e612d1081909eced7a1ebd28692 |
completed | May 15, 2026, 12:15 p.m. |
| NEDg | Description generation | batch_6a070f03caec8190a93334cc01914015 |
completed | May 15, 2026, 12:18 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a070f69fecc8190a5a9195b1701f653 |
completed | May 15, 2026, 12:19 p.m. |
Created at: April 10, 2026, 1:21 p.m.