Triple
T33578347
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Britain's Got Talent audition performance of "I Dreamed a Dream" |
E860086
|
entity |
| Predicate | firstAiredInMonth |
P129291
|
FINISHED |
| Object | April 2009 |
—
|
LITERAL 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: April 2009 | Statement: [Britain's Got Talent audition performance of "I Dreamed a Dream", firstAiredInMonth, April 2009]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstAiredInMonth Context triple: [Britain's Got Talent audition performance of "I Dreamed a Dream", firstAiredInMonth, April 2009]
-
A.
firstAppearanceMonth
chosen
Indicates the month in which an entity first appeared or was introduced.
-
B.
firstAiredInSeason
Indicates the specific season of a series in which an episode or content item was originally first broadcast or released.
-
C.
firstAired
Indicates the date on which something (such as a show, episode, or broadcast content) was first aired or publicly transmitted.
-
D.
commandedAsFirstMonthIn
Indicates that an entity is designated or ordered to serve as the first month within a specified temporal system or context.
-
E.
announcedInMonth
Indicates that an announcement or declaration occurred during a specified calendar month.
- F. None of above.
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_69f3497d37848190afcbb5ef3f5c7376 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a037c8ae0248190b7e2ce4bf852c22d |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379f505c88190ac0879ab422c3054 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:40 a.m.