Triple
T2562624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mandarin phonology |
E57275
|
entity |
| Predicate | hasCodaTypes |
P40499
|
FINISHED |
| Object | vowel coda |
—
|
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: vowel coda | Statement: [Mandarin phonology, hasCodaTypes, vowel coda]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCodaTypes Context triple: [Mandarin phonology, hasCodaTypes, vowel coda]
-
A.
hasTypeSystem
Indicates that an entity employs, is governed by, or is associated with a particular type system (a defined set of rules for classifying and constraining types).
-
B.
hasParType
Indicates that an entity has a specific parent type or category to which it belongs.
-
C.
hasCommunicationCodeType
Indicates that an entity is associated with a specific type or category of communication code (e.g., phone, fax, email, messaging).
-
D.
hasNotableType
Indicates that an entity is associated with a specific notable category or type that characterizes its significance or role.
-
E.
hasCapitalType
Indicates that a specified location’s capital is of a particular type (e.g., political, administrative, or economic capital).
- F. None of above. chosen
Provenance (4 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_69ab4a4ef9008190a0e6d4422b9418b7 |
completed | March 6, 2026, 9:42 p.m. |
| NER | Named-entity recognition | batch_69abd35c6ee88190b6eaa1841d3e99a4 |
completed | March 7, 2026, 7:27 a.m. |
| PD | Predicate disambiguation | batch_69abd0caeb488190b0dd8e48d0f2777d |
completed | March 7, 2026, 7:16 a.m. |
| PDg | Predicate description generation | batch_69abd35b216881908f4ef32d1c1e5080 |
completed | March 7, 2026, 7:27 a.m. |
Created at: March 6, 2026, 9:48 p.m.