Triple
T22071365
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hugh Downs |
E545413
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Today |
—
|
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: Today | Statement: [Hugh Downs, notableWork, Today]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Today Context triple: [Hugh Downs, notableWork, Today]
-
A.
Today
"Today" is a pioneering 1929 Soviet documentary film by Esfir Shub that exemplifies her innovative use of found footage to deliver sharp social and political commentary.
-
B.
Today
"Today" is an R&B song by American singer Musiq Soulchild (formerly known as Luvanmusiq), featured on one of his mid-2000s albums.
-
C.
Today
"Today" is an Iranian drama film by director Reza Mirkarimi that follows a Tehran taxi driver whose routine day is upended when he helps a pregnant woman in distress.
-
D.
Today
chosen
Today is a long-running American morning news and talk show on NBC featuring news coverage, interviews, and lifestyle segments.
-
E.
Today
Today is BBC Radio 4’s leading early-morning news and current affairs programme, featuring in-depth interviews, reports, and analysis of national and international events.
- 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_69e11e344dfc81909b1d88a7221329c7 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12888dcc08190b18d3d44d09ab943 |
completed | April 28, 2026, 9:37 p.m. |
Created at: April 16, 2026, 8:28 p.m.