Triple
T8565173
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Balu Mahendra |
E202783
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Kokila |
E742942
|
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: Kokila | Statement: [Balu Mahendra, directed, Kokila]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kokila Context triple: [Balu Mahendra, directed, Kokila]
-
A.
Kokila
chosen
Kokila is a critically acclaimed Indian film directed by Balu Mahendra, known for its realistic storytelling and evocative cinematography.
-
B.
Kokila
Kokila is an imprint of Penguin Random House dedicated to publishing diverse, inclusive, and socially conscious books for children and young adults.
-
C.
Sukierae
Sukierae is a 2014 double album by Jeff Tweedy and his son Spencer, blending introspective songwriting with experimental indie rock arrangements.
-
D.
Kumara
Kumara is another name for Kartikeya, the Hindu god of war and the son of Shiva and Parvati, widely revered in South India and Sri Lanka.
-
E.
Korina
Korina is the surname of Irina Korina, a contemporary Russian artist known for her installations and sculptural works.
- 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_69ca8327b0a881908606ff860713964d |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe9d2331881909d92ddde90f580e9 |
completed | March 31, 2026, 3:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cea87badf081909727808f0e14ae45 |
completed | April 2, 2026, 5:33 p.m. |
Created at: March 30, 2026, 6:20 p.m.