Triple
T21593254
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | J. S. Aurora |
E532832
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Jagjit |
—
|
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: Jagjit | Statement: [J. S. Aurora, givenName, Jagjit]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jagjit Context triple: [J. S. Aurora, givenName, Jagjit]
-
A.
Jagjit
chosen
Jagjit is the given name of Jagjit Singh Aurora, a prominent Indian Army general best known for his leadership in the 1971 Indo-Pakistani War that led to the creation of Bangladesh.
-
B.
Balbir
Balbir is the given first name of the Indian actor and film producer Shashi Kapoor.
-
C.
Amarjeet
Amarjeet is a Canadian politician best known as Amarjeet Sohi, who has served as mayor of Edmonton and as a federal cabinet minister.
-
D.
Jagmal Singh
Jagmal Singh was a 16th-century Rajput prince of Mewar, known as the disputed successor of Maharana Udai Singh II and for later serving under the Mughal Empire.
-
E.
Indar Jit Rikhye
Indar Jit Rikhye was an Indian Army officer and prominent United Nations military adviser known for his leadership roles in UN peacekeeping operations.
- 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_69e0c46251648190876f0427cf2d321b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eefadf6e608190b42b26ea22c76ec6 |
completed | April 27, 2026, 5:57 a.m. |
Created at: April 16, 2026, 6:32 p.m.