Triple
T7730589
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manda–Pengo subgroup |
E175238
|
entity |
| Predicate | linguisticResearchArea |
P29095
|
FINISHED |
| Object | historical-comparative Dravidian linguistics |
—
|
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: historical-comparative Dravidian linguistics | Statement: [Manda–Pengo subgroup, linguisticResearchArea, historical-comparative Dravidian linguistics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: linguisticResearchArea Context triple: [Manda–Pengo subgroup, linguisticResearchArea, historical-comparative Dravidian linguistics]
-
A.
linguisticField
chosen
Indicates that something pertains to or is associated with a particular area or subdiscipline within linguistics.
-
B.
linguisticArea
Indicates a regional context in which languages share features due to geographic proximity and contact rather than common genetic origin.
-
C.
linguisticClassification
Indicates the relationship by which an entity is categorized according to its language or linguistic type.
-
D.
hasLinguisticTypology
Indicates a relationship where a language or linguistic system is characterized by a specific typological classification or structural type.
-
E.
linguisticScope
Indicates the range or domain within language (such as a phrase, clause, or discourse segment) over which a particular linguistic element, feature, or operation has effect.
- 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_69c6995e912c81909a49a2657103f786 |
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, 4:06 p.m.