Triple
T5134582
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fengtian |
E115788
|
entity |
| Predicate | romanizationVariant |
P5923
|
FINISHED |
| Object | Feng-tien-fu |
E496849
|
NE FINISHED |
How this triple was built (2 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: Feng-tien-fu | Statement: [Fengtian, romanizationVariant, Feng-tien-fu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Feng-tien-fu Context triple: [Fengtian, romanizationVariant, Feng-tien-fu]
-
A.
Feng-tien
chosen
Feng-tien is an older romanized form of the name Fengtian, historically used for the city now known as Shenyang in northeastern China.
-
B.
Foxiangge
Foxiangge is the Tower of Buddhist Incense, a prominent multi-story pavilion and iconic landmark within Beijing’s Summer Palace complex.
-
C.
Kwang-chou
Kwang-chou is an alternative romanization of Guangzhou, the major port city and economic hub in southern China historically known in the West as Canton.
-
D.
Hsia-men
Hsia-men is an older romanized form of the name for Xiamen, a major port city on the southeast coast of China in Fujian Province.
-
E.
Feng
Feng is a Chinese surname borne by various notable figures in Chinese history and culture.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69bd44459a988190a772a5c2ec6a1965 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd784e306081908dd8317227227807 |
completed | March 20, 2026, 4:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69becfdd965c8190adda020ead81bd05 |
completed | March 21, 2026, 5:05 p.m. |
Created at: March 20, 2026, 1:43 p.m.