Triple
T13267215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Humenné |
E315952
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object |
Munkacs
Munkacs is a historic city in western Ukraine, known today as Mukachevo, noted for its multicultural heritage and prominent medieval castle.
|
E1031264
|
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: Munkacs | Statement: [Humenné, hasTwinTown, Munkacs]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Munkacs Context triple: [Humenné, hasTwinTown, Munkacs]
-
A.
Mundruczó
Mundruczó is the surname of Hungarian film and theatre director Kornél Mundruczó, known for his innovative and often provocative works.
-
B.
Menczel
Menczel is a variant spelling of the surname Menzel, which is of German origin and borne by various notable individuals.
-
C.
Maszovlet
Maszovlet was the state-owned Hungarian-Soviet civil aviation company that served as Hungary’s national airline in the early post–World War II period before becoming Malév Hungarian Airlines.
-
D.
Harkányi
Harkányi is a Hungarian surname associated with individuals such as Mici Mária Harkányi.
-
E.
Mány
Mány is a village in Fejér County, Hungary, situated in the Transdanubian region west of Budapest.
- 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: Munkacs Triple: [Humenné, hasTwinTown, Munkacs]
Generated description
Munkacs is a historic city in western Ukraine, known today as Mukachevo, noted for its multicultural heritage and prominent medieval castle.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Munkacs Target entity description: Munkacs is a historic city in western Ukraine, known today as Mukachevo, noted for its multicultural heritage and prominent medieval castle.
-
A.
Mundruczó
Mundruczó is the surname of Hungarian film and theatre director Kornél Mundruczó, known for his innovative and often provocative works.
-
B.
Menczel
Menczel is a variant spelling of the surname Menzel, which is of German origin and borne by various notable individuals.
-
C.
Maszovlet
Maszovlet was the state-owned Hungarian-Soviet civil aviation company that served as Hungary’s national airline in the early post–World War II period before becoming Malév Hungarian Airlines.
-
D.
Harkányi
Harkányi is a Hungarian surname associated with individuals such as Mici Mária Harkányi.
-
E.
Mány
Mány is a village in Fejér County, Hungary, situated in the Transdanubian region west of Budapest.
- 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_69d806b1d9ac8190852c5571d5bd5f0f |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d9901e44bc8190966f87ae219d6bf4 |
completed | April 11, 2026, 12:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f70a4cc20881909b1ca6623e5b1988 |
completed | May 3, 2026, 8:41 a.m. |
| NEDg | Description generation | batch_69f70bc5111c8190ae5b098c806bb845 |
completed | May 3, 2026, 8:48 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f70ca343f08190b6484f464ed40810 |
completed | May 3, 2026, 8:51 a.m. |
Created at: April 9, 2026, 9:25 p.m.