Triple
T28722022
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Freddy Freeman (Shazam! 2019 film) |
E730120
|
entity |
| Predicate | films |
P150261
|
FINISHED |
| Object | videos of Shazam using powers |
—
|
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: videos of Shazam using powers | Statement: [Freddy Freeman (Shazam! 2019 film), films, videos of Shazam using powers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: films Context triple: [Freddy Freeman (Shazam! 2019 film), films, videos of Shazam using powers]
-
A.
film
Indicates that an entity is a movie or cinematic work, or that a relationship involves such a movie.
-
B.
filmBase
Indicates the primary location or headquarters from which a film-related entity (such as a production, company, or operation) is based or operates.
-
C.
filmContent
chosen
Indicates that one entity is the substantive material or subject matter contained within a film.
-
D.
filmWon
Indicates that a film has received or been awarded a particular prize, honor, or recognition.
-
E.
filmMedium
Indicates the physical or technical format (such as film stock, digital, or video) in which a film is recorded or presented.
- 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_69f043e91fe48190b73bcd8e08d433e0 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f657099ccc8190a2b92a395f5436e7 |
completed | May 2, 2026, 7:56 p.m. |
| PD | Predicate disambiguation | batch_69f651ac855481908e30c3b345d31356 |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 5:54 a.m.