Triple
T7724164
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ma |
E175086
|
entity |
| Predicate | hasSimplifiedForm |
P52959
|
FINISHED |
| Object | 马 |
—
|
LITERAL 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: 马 | Statement: [Ma, hasSimplifiedForm, 马]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSimplifiedForm Context triple: [Ma, hasSimplifiedForm, 马]
-
A.
simplifiedForm
chosen
Indicates that one entity is a reduced or less complex version of another, preserving essential meaning while omitting detail or complexity.
-
B.
hasClosedForm
Indicates that a mathematical expression, function, or solution can be written in a finite, explicit form using a standard set of operations and well-known functions.
-
C.
hasSymbolicForm
Indicates that one entity serves as the symbolic representation or abstract form of another entity.
-
D.
isCanonicalFormOf
Indicates that one entity is the standard or officially accepted form or representation of another, often more variant, entity.
-
E.
simplifiesEquation
Indicates that one entity performs an operation that reduces an equation to a simpler or more manageable form while preserving its equivalence.
- 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_69c6995d541c81909eaa646b1a8369a9 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7074eca4c8190bd51fd1b450729e8 |
completed | March 27, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69c7016a6cf88190b53bf4b958f0f302 |
completed | March 27, 2026, 10:15 p.m. |
Created at: March 27, 2026, 4:05 p.m.