Triple
T28593474
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tamil Wikipedia |
E723714
|
entity |
| Predicate | hasSisterProjects |
P81956
|
FINISHED |
| Object | Tamil Wiktionary |
—
|
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: Tamil Wiktionary | Statement: [Tamil Wikipedia, hasSisterProjects, Tamil Wiktionary]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSisterProjects Context triple: [Tamil Wikipedia, hasSisterProjects, Tamil Wiktionary]
-
A.
isSisterProjectOf
chosen
Indicates that two projects are related and aligned in purpose or scope, typically operating in parallel under a common umbrella or organization.
-
B.
hasSisterOrganization
Indicates that one organization is related to another as a sister organization, typically sharing a common parent, affiliation, or parallel status within the same overarching structure.
-
C.
hasSister
Indicates that one entity is the sister of another entity.
-
D.
hasSisterSite
Indicates that one site is formally associated with another as a sister site, typically implying a parallel or closely related counterpart.
-
E.
hasSisterCommunity
Indicates a formal or recognized partnership relationship between two communities, often for mutual support, exchange, or collaboration.
- 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_69f01d80b1908190980594837604b8c7 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f7221dc9a88190bb8194fcc29c42bc |
completed | May 3, 2026, 10:23 a.m. |
| PD | Predicate disambiguation | batch_69f72153a9188190b02adc84e1be4af8 |
completed | May 3, 2026, 10:20 a.m. |
Created at: April 28, 2026, 4:21 a.m.