Triple
T9633579
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maya Soetoro-Ng |
E232866
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object | Savita Ng |
E232866
|
NE 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: Savita Ng | Statement: [Maya Soetoro-Ng, hasChild, Savita Ng]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Savita Ng Context triple: [Maya Soetoro-Ng, hasChild, Savita Ng]
-
A.
Savita Ng
chosen
Savita Ng is the daughter of educator Maya Soetoro-Ng, who is the half-sister of former U.S. President Barack Obama.
-
B.
Persis Khambatta
Persis Khambatta was an Indian model and actress best known internationally for her role as Lieutenant Ilia in "Star Trek: The Motion Picture."
-
C.
Parvati Nair
Parvati Nair is an Indian actress and model known for her work in South Indian cinema, particularly in Malayalam and Tamil films.
-
D.
Chitra Singh
Chitra Singh is an acclaimed Indian ghazal singer, best known for her soulful duets with her late husband Jagjit Singh and for popularizing modern ghazal music.
-
E.
Shyamala Maisondieu
Shyamala Maisondieu is a renowned perfumer known for creating modern, sophisticated fragrances for major luxury brands.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca848940cc8190b97cec654cb3bb4a |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9b28ce2c819086d3c6e4e6ea95a7 |
completed | April 1, 2026, 10:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d18232e34c8190a19685ee9210e88b |
completed | April 4, 2026, 9:27 p.m. |
Created at: March 30, 2026, 8:11 p.m.