Triple
T31908524
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern Khalaj |
E814618
|
entity |
| Predicate | lessUsedInDomain |
P89202
|
FINISHED |
| Object | formal education |
—
|
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: formal education | Statement: [Southern Khalaj, lessUsedInDomain, formal education]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lessUsedInDomain Context triple: [Southern Khalaj, lessUsedInDomain, formal education]
-
A.
notUsedInDomain
Indicates that a given element or resource is not utilized, referenced, or applicable within a specified domain or context.
-
B.
usedInDomain
Indicates that something (such as a concept, method, or resource) is applied or utilized within a particular domain or field.
-
C.
usedLessIn
chosen
Indicates that one entity is used with a lower frequency or intensity compared to another entity.
-
D.
usedAsDomainHack
Indicates that a domain name is intentionally chosen or formatted so that its full text (including the top-level domain) forms a meaningful word or phrase, effectively "hacking" the domain structure for semantic or branding purposes.
-
E.
notUsedOver
Indicates that one entity has not been used, applied, or utilized for a duration exceeding a specified time period relative to another entity or reference point.
- 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_69f348f109d88190b5005372c53d2fcd |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b1b6a1f08190b1d5306ae35977cb |
completed | May 3, 2026, 2:23 a.m. |
| PD | Predicate disambiguation | batch_69f6aca59d4881908d14ed47962703bd |
completed | May 3, 2026, 2:02 a.m. |
Created at: May 1, 2026, 12:01 a.m.