Triple
T11681444
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Huang Hua |
E277623
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
He Liliang
He Liliang was the wife of Chinese diplomat and former foreign minister Huang Hua.
|
E940638
|
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: He Liliang | Statement: [Huang Hua, spouse, He Liliang]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: He Liliang Context triple: [Huang Hua, spouse, He Liliang]
-
A.
Hòu Liáng
Hòu Liáng refers to the Later Liang dynasty, a short-lived Chinese regime during the Five Dynasties and Ten Kingdoms period that ruled parts of northern China in the late ninth and early tenth centuries.
-
B.
He Saifei
He Saifei is a Chinese actress known for her roles in acclaimed films and television dramas, particularly in period and art-house cinema.
-
C.
Mã Liềng
Mã Liềng is a subgroup of the Chut ethnic community in Vietnam, known for its distinct language and traditional highland lifestyle.
-
D.
Tianhan
Tianhan was an era name used during the reign of Emperor Wu of the Western Han dynasty in ancient China.
-
E.
Liang
Liang is a common Chinese surname borne by numerous historical figures, scholars, and public personalities across the Chinese-speaking world.
- 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: He Liliang Triple: [Huang Hua, spouse, He Liliang]
Generated description
He Liliang was the wife of Chinese diplomat and former foreign minister Huang Hua.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: He Liliang Target entity description: He Liliang was the wife of Chinese diplomat and former foreign minister Huang Hua.
-
A.
Hòu Liáng
Hòu Liáng refers to the Later Liang dynasty, a short-lived Chinese regime during the Five Dynasties and Ten Kingdoms period that ruled parts of northern China in the late ninth and early tenth centuries.
-
B.
He Saifei
He Saifei is a Chinese actress known for her roles in acclaimed films and television dramas, particularly in period and art-house cinema.
-
C.
Mã Liềng
Mã Liềng is a subgroup of the Chut ethnic community in Vietnam, known for its distinct language and traditional highland lifestyle.
-
D.
Tianhan
Tianhan was an era name used during the reign of Emperor Wu of the Western Han dynasty in ancient China.
-
E.
Liang
Liang is a common Chinese surname borne by numerous historical figures, scholars, and public personalities across the Chinese-speaking world.
- 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_69d6aafd0a448190b44da30af8c6c519 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a462bb2881909238107d34c0a28d |
completed | April 10, 2026, 7:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ef141134bc81908c0cfb0a3711c115 |
completed | April 27, 2026, 7:45 a.m. |
| NEDg | Description generation | batch_69ef35527f908190b681afdae3aec319 |
completed | April 27, 2026, 10:07 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ef51ec07ec8190b5cd97cf909388f0 |
completed | April 27, 2026, 12:09 p.m. |
Created at: April 8, 2026, 9:40 p.m.