Triple
T21943897
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irrfan Khan |
E541887
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Piku |
—
|
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: Piku | Statement: [Irrfan Khan, notableWork, Piku]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Piku Context triple: [Irrfan Khan, notableWork, Piku]
-
A.
Piku
chosen
Piku is a 2015 Indian comedy-drama film centered on the relationship between a headstrong daughter and her aging, hypochondriac father, featuring a notable performance by Amitabh Bachchan.
-
B.
Pukinin
Pukinin is a village located in Rawa County in central Poland.
-
C.
Pipikoro
Pipikoro is an Austronesian language spoken in Central Sulawesi, Indonesia, known locally as an alternate name for the Uma language.
-
D.
Pichanaki
Pichanaki is a prominent town in central Peru known for its agricultural activity, especially coffee production, within the Amazonian high jungle region.
-
E.
Pinukpuk
Pinukpuk is a rural municipality in the province of Kalinga in the Philippines, known for its mountainous terrain and predominantly indigenous communities.
- 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_69e0c47e2e5c81909a7f74ce3de50911 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1242515ec8190b015bf8c7b13be85 |
completed | April 28, 2026, 9:18 p.m. |
Created at: April 16, 2026, 7:56 p.m.