Triple
T29299143
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jason Sanjay |
E742911
|
entity |
| Predicate | motherCitizenshipBackground |
P16974
|
FINISHED |
| Object | Sri Lankan Tamil origin |
—
|
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: Sri Lankan Tamil origin | Statement: [Jason Sanjay, motherCitizenshipBackground, Sri Lankan Tamil origin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: motherCitizenshipBackground Context triple: [Jason Sanjay, motherCitizenshipBackground, Sri Lankan Tamil origin]
-
A.
hasMotherCitizenship
Indicates that the mother of a given person holds citizenship in a specified country or jurisdiction.
-
B.
motherNationality
chosen
Indicates the country or national identity associated with a person's mother.
-
C.
countryOfCitizenship
Indicates the country in which a person or entity holds legal citizenship.
-
D.
hasFatherCitizenship
Indicates that the citizenship of a person’s father is associated with or attributed to that person.
-
E.
hasAncestralCitizenshipOf
Indicates that an entity holds or is recognized as holding citizenship of another entity based on ancestral or lineage connections rather than solely on birth or residence.
- 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_69f09123ed9881909f351f7541933f5e |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69f665a083548190ae8b9c9203dcf3b0 |
completed | May 2, 2026, 8:59 p.m. |
| PD | Predicate disambiguation | batch_69f663362c008190a22afed262f1e426 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 1:09 p.m.