Triple
T16514576
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Indian princes |
E401148
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | Holkar |
E394101
|
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: Holkar | Statement: [Indian princes, title, Holkar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Holkar Context triple: [Indian princes, title, Holkar]
-
A.
Holkar
chosen
Holkar refers to a prominent Maratha dynasty that ruled the Indore State in central India and played a significant role in 18th- and 19th-century Indian politics.
-
B.
Talwandi Bhai
Talwandi Bhai is a small town in Punjab, India, known primarily as an agricultural and grain market hub.
-
C.
Behari
Behari is a fictional character, likely from South Asian literature or drama, connected to the character Ashalata in a significant narrative relationship.
-
D.
Harsil
Harsil is a serene Himalayan village in Uttarakhand, India, known for its apple orchards, scenic river valley, and as a stopover on the route to the Gangotri temple.
-
E.
Khostwal
Khostwal is a Pashtun tribe belonging to the Karlani tribal confederation, primarily found in parts of Afghanistan and Pakistan.
- 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_69d883838abc8190bc79cb2d41733ce2 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32e7a5ff88190984e2f2bc2fd17cc |
completed | April 18, 2026, 7:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a006084949081909e8cdfeafa7564de |
completed | May 10, 2026, 10:40 a.m. |
Created at: April 10, 2026, 5:14 a.m.