Triple
T23340682
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | H. H. Kung |
E591726
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
Kung
Kung is a Chinese surname historically associated with prominent political and business figures, including influential members of the Republic of China era.
|
E1581860
|
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: Kung | Statement: [H. H. Kung, familyName, Kung]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kung Context triple: [H. H. Kung, familyName, Kung]
-
A.
Kung Sor
Kung Sor is the traditional assembly hall attached to Hong Kong’s historic Man Mo Temple, historically used as a community meeting place and venue for settling local disputes.
-
B.
KONG
KONG is a television station in the Seattle–Tacoma market, commonly associated with KING-TV as its sister station.
-
C.
Manky Kong
Manky Kong is a minor antagonist in the Donkey Kong series, depicted as a disgruntled, barrel-throwing member of the Kong species who opposes Donkey and Diddy Kong.
-
D.
Kongen
Kongen is a prominent mountain peak in Norway’s Romsdalen valley, known for its striking alpine profile and popular climbing routes.
-
E.
Kong-sang
Kong-sang is the given name of Chan Kong-sang, better known worldwide as the Hong Kong martial artist and film star Jackie Chan.
- 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: Kung Triple: [H. H. Kung, familyName, Kung]
Generated description
Kung is a Chinese surname historically associated with prominent political and business figures, including influential members of the Republic of China era.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kung Target entity description: Kung is a Chinese surname historically associated with prominent political and business figures, including influential members of the Republic of China era.
-
A.
Kung Sor
Kung Sor is the traditional assembly hall attached to Hong Kong’s historic Man Mo Temple, historically used as a community meeting place and venue for settling local disputes.
-
B.
KONG
KONG is a television station in the Seattle–Tacoma market, commonly associated with KING-TV as its sister station.
-
C.
Manky Kong
Manky Kong is a minor antagonist in the Donkey Kong series, depicted as a disgruntled, barrel-throwing member of the Kong species who opposes Donkey and Diddy Kong.
-
D.
Kongen
Kongen is a prominent mountain peak in Norway’s Romsdalen valley, known for its striking alpine profile and popular climbing routes.
-
E.
Kong-sang
Kong-sang is the given name of Chan Kong-sang, better known worldwide as the Hong Kong martial artist and film star Jackie Chan.
- 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_69e25d20e3d08190bcede87673cafb25 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f198329d9c8190992627afa9b54bed |
completed | April 29, 2026, 5:33 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c4cb61d688190970ccb33d82c0fdd |
completed | May 19, 2026, 11:42 a.m. |
| NEDg | Description generation | batch_6a0c4e915358819097b8c0b69b2a490f |
completed | May 19, 2026, 11:50 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c52a1b82c81909c27a1cde973ae44 |
completed | May 19, 2026, 12:08 p.m. |
Created at: April 17, 2026, 5:18 p.m.