Triple
T19273289
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ankur |
E481982
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | Bhanudas Divakar |
—
|
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: Bhanudas Divakar | Statement: [Ankur, editedBy, Bhanudas Divakar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bhanudas Divakar Context triple: [Ankur, editedBy, Bhanudas Divakar]
-
A.
Bhanudas Divakar
chosen
Bhanudas Divakar is an editor known for his work on the Indian film "Manthan."
-
B.
Jivatram Bhagwandas
Jivatram Bhagwandas was the full name of J. B. Kripalani, a prominent Indian independence activist and politician who served as president of the Indian National Congress.
-
C.
Sudh Mahadev
Sudh Mahadev is a revered Hindu temple and pilgrimage site in the Jammu region of India, known for its ancient Shiva shrine and scenic Himalayan surroundings.
-
D.
Gopal Narayan
Gopal Narayan is a person whose given name includes the element "Narayan," a traditional Indian name often associated with the Hindu deity Vishnu.
-
E.
Madan Lal Khurana
Madan Lal Khurana was an Indian politician from the Bharatiya Janata Party who played a key role in Delhi’s political landscape and also served in various national-level positions.
- 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_69d8e8ce54cc8190998418ff1f66ef28 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fbba7758819081c1c78667c59c5e |
completed | April 20, 2026, 10:11 a.m. |
Created at: April 10, 2026, 1:29 p.m.