Triple
T19376515
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 何 |
E484681
|
entity |
| Predicate | romanizationWadeGiles |
P51399
|
FINISHED |
| Object | Ho |
—
|
NE NERFINISHED |
How this triple was built (3 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: Ho | Statement: [何, romanizationWadeGiles, Ho]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ho Context triple: [何, romanizationWadeGiles, Ho]
-
A.
Ho
Ho are an indigenous Adivasi community of eastern India, primarily inhabiting parts of Jharkhand and Odisha, known for their Austroasiatic Ho language and distinct cultural traditions.
-
B.
Ho
Ho is a town in southeastern Ghana that serves as the capital of the Volta Region and an important administrative and commercial center.
-
C.
Ho
Ho is the given name of the Korean-born contemporary artist Do Ho Suh, known for his large-scale installations exploring space, memory, and identity.
-
D.
Ho
chosen
Ho is a common East Asian surname used in various cultures, including Chinese and Korean, often representing different characters and lineages depending on the language and region.
-
E.
Ho
"Ho" is a track featured on Ludacris's debut studio album "Back for the First Time."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: romanizationWadeGiles Context triple: [何, romanizationWadeGiles, Ho]
-
A.
WadeGilesForm
chosen
Indicates that one entity is the Wade–Giles romanized form corresponding to another entity’s written or spoken Chinese form.
-
B.
romanizationFrom
Indicates that one entity is a romanized representation derived from the script or writing system of another entity.
-
C.
yueRomanization
Indicates that an entity is represented or written using the Cantonese (Yue) romanization system.
-
D.
ChinesePinyin
Indicates that one entity is the Chinese pinyin (romanized phonetic transcription) representation of another entity.
-
E.
romanizationType
Indicates the specific system or method used to convert text from one writing system into its Roman (Latin) alphabet representation.
- F. None of above.
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_69d8e8d460d88190abf0591c5c9d2b0c |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e61a5cfbf48190ac60e3ffa6baa263 |
completed | April 20, 2026, 12:21 p.m. |
| PD | Predicate disambiguation | batch_69e4fd54f8e48190956e73dd8969164a |
completed | April 19, 2026, 4:05 p.m. |
Created at: April 10, 2026, 1:35 p.m.