Triple
T22831586
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rosita |
E565814
|
entity |
| Predicate | friendsWith |
P8712
|
FINISHED |
| Object | Meena |
—
|
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: Meena | Statement: [Rosita, friendsWith, Meena]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Meena Context triple: [Rosita, friendsWith, Meena]
-
A.
Meena
chosen
Meena is a shy teenage elephant with a powerful singing voice in the animated film "Sing."
-
B.
Meena
Meena is an Indian actress known for her extensive work in South Indian cinema, particularly in Tamil and Malayalam films.
-
C.
Madhavi
Madhavi is a celebrated courtesan and pivotal literary figure in ancient Tamil epic tradition, prominently featured in the Sangam-era works Silappatikaram and its sequel Manimekalai.
-
D.
Manjula
Manjula is a central figure in the 1965 film "Shakespeare-Wallah," representing the personal and cultural tensions faced by an Anglo-Indian theatre troupe in post-colonial India.
-
E.
Anasuya
Anasuya is a revered sage and exemplar of chastity and devotion in Hindu tradition, celebrated as the wife of the rishi Atri and mother of the divine Trimurti incarnations.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e24585ab1c81909b2b5065d15805d5 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17e2bcad8819091f237fd2273a20c |
completed | April 29, 2026, 3:42 a.m. |
Created at: April 17, 2026, 3:34 p.m.