Triple
T4032644
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dream Sports |
E83750
|
entity |
| Predicate | hasSubsidiary |
P254
|
FINISHED |
| Object | FanCode |
E409047
|
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: FanCode | Statement: [Dream Sports, hasSubsidiary, FanCode]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: FanCode Context triple: [Dream Sports, hasSubsidiary, FanCode]
-
A.
FanCode
chosen
FanCode is an Indian digital sports platform offering live streaming, scores, and content for a wide range of sports and leagues.
-
B.
Fandom
Fandom is a fan-focused entertainment and gaming platform best known for hosting community-created wikis and content about movies, TV, games, and pop culture.
-
C.
Bleacher Report
Bleacher Report is a digital sports media company known for its real-time coverage, analysis, and social-first content across major sports and leagues.
-
D.
NFF
NFF is the commonly used abbreviation for the Nigeria Football Federation, the governing body of football in Nigeria.
-
E.
NFF
NFF is the abbreviation for the Netherlands Film Festival, an annual event celebrating Dutch cinema and filmmakers.
- 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_69aed92e29ac819080f7a98b594fec05 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefb0f776881909db6b7df1db7664c |
completed | March 9, 2026, 4:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5629748d88190984cce08eef05e9c |
completed | March 14, 2026, 1:28 p.m. |
Created at: March 9, 2026, 3:36 p.m.