Triple
T21110048
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hum Awards (film categories) |
E520146
|
entity |
| Predicate | network |
P2637
|
FINISHED |
| Object | Hum TV |
—
|
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: Hum TV | Statement: [Hum Awards (film categories), network, Hum TV]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hum TV Context triple: [Hum Awards (film categories), network, Hum TV]
-
A.
Hum TV
chosen
Hum TV is a Pakistani entertainment television network best known for producing and broadcasting popular drama serials and organizing the annual Hum Awards.
-
B.
HTV
HTV is a Japanese uncrewed cargo spacecraft, also known as the H-II Transfer Vehicle, used to deliver supplies to the International Space Station.
-
C.
HTV
HTV was a British regional television company and ITV franchise holder serving Wales and the West of England.
-
D.
IGN TV
IGN TV is a video-focused arm of IGN that produces and hosts entertainment and gaming-related shows, reviews, and original video content.
-
E.
TVH
TVH is an Indian real estate and infrastructure development company known for sponsoring chess legend Viswanathan Anand.
- 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_69e0b509a318819092fbbcb21d1fe603 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7210110a48190a6359b6732f6293d |
completed | April 21, 2026, 7:02 a.m. |
Created at: April 16, 2026, 2:54 p.m.