Triple
T38386073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gaeml |
E899582
|
entity |
| Predicate | belongsToMacroFamilyOfSpeakers |
P89917
|
FINISHED |
| Object | Kra–Dai languages |
—
|
NE NERFINISHED |
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: Kra–Dai languages | Statement: [Gaeml, belongsToMacroFamilyOfSpeakers, Kra–Dai languages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: belongsToMacroFamilyOfSpeakers Context triple: [Gaeml, belongsToMacroFamilyOfSpeakers, Kra–Dai languages]
-
A.
belongsToMacrofamily
chosen
Indicates that a language is classified as part of a larger proposed language macrofamily.
-
B.
macrolanguageMemberOf
Indicates that a language variety is classified as a member of a larger macrolanguage grouping.
-
C.
sharesLinguisticFamilyWith
Indicates that two languages belong to the same linguistic family or branch within a language family.
-
D.
possiblyRepresentsLanguageFamily
Indicates that one entity may, but does not certainly, denote or correspond to the language family of the other entity.
-
E.
languageFamilyAssociated
Indicates that there is an association or connection between a language and a particular language family.
- 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_69f76e5c9b808190b486523f5c2f817d |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a005b2e0a9c819081c6f7ccbef49ff8 |
completed | May 10, 2026, 10:17 a.m. |
| PD | Predicate disambiguation | batch_6a005a8bcde88190ace2bc0215e26430 |
completed | May 10, 2026, 10:14 a.m. |
Created at: May 3, 2026, 4:31 p.m.