Triple
T15591365
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Teng |
E374749
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object |
Teng Yu-yu
Teng Yu-yu is a Taiwanese film editor known for her work on several acclaimed Chinese-language films.
|
E1201515
|
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: Teng Yu-yu | Statement: [Teng, hasNotableBearer, Teng Yu-yu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Teng Yu-yu Context triple: [Teng, hasNotableBearer, Teng Yu-yu]
-
A.
Yen Yu-yun
Yen Yu-yun was a Chinese socialite and diplomat’s wife best known as the spouse of prominent Chinese statesman V. K. Wellington Koo.
-
B.
Teng Yu-ting
Teng Yu-ting is a Taiwanese taekwondo practitioner known for competing at the international level, including major multi-sport events.
-
C.
Teng Yu-yao
Teng Yu-yao is a person notable for bearing the Chinese surname Teng.
-
D.
Teng Yu-ying
Teng Yu-ying is a notable individual who bears the Chinese surname Teng and is recognized for achievements significant enough to be recorded under that family name.
-
E.
Teng Yu-han
Teng Yu-han is a person notable for bearing the surname Teng.
- 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: Teng Yu-yu Triple: [Teng, hasNotableBearer, Teng Yu-yu]
Generated description
Teng Yu-yu is a Taiwanese film editor known for her work on several acclaimed Chinese-language films.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Teng Yu-yu Target entity description: Teng Yu-yu is a Taiwanese film editor known for her work on several acclaimed Chinese-language films.
-
A.
Yen Yu-yun
Yen Yu-yun was a Chinese socialite and diplomat’s wife best known as the spouse of prominent Chinese statesman V. K. Wellington Koo.
-
B.
Teng Yu-ting
Teng Yu-ting is a Taiwanese taekwondo practitioner known for competing at the international level, including major multi-sport events.
-
C.
Teng Yu-yao
Teng Yu-yao is a person notable for bearing the Chinese surname Teng.
-
D.
Teng Yu-ying
Teng Yu-ying is a notable individual who bears the Chinese surname Teng and is recognized for achievements significant enough to be recorded under that family name.
-
E.
Teng Yu-han
Teng Yu-han is a person notable for bearing the surname Teng.
- 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_69d85cce25008190b13b52745fbd719b |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e4b903c8190a35f9267cb38e721 |
completed | April 16, 2026, 2:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0007757ed48190813f6ab839240a15 |
completed | May 10, 2026, 4:20 a.m. |
| NEDg | Description generation | batch_6a000bd836f081909ee477fd311c3295 |
completed | May 10, 2026, 4:38 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a000c33963c8190a00271fb732c5b50 |
completed | May 10, 2026, 4:40 a.m. |
Created at: April 10, 2026, 4:11 a.m.