Triple
T14627674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mamma Mia! 2: Here We Go Again |
E343393
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Hugh Skinner |
E268980
|
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: Hugh Skinner | Statement: [Mamma Mia! 2: Here We Go Again, stars, Hugh Skinner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hugh Skinner Context triple: [Mamma Mia! 2: Here We Go Again, stars, Hugh Skinner]
-
A.
Hugh Skinner
chosen
Hugh Skinner is a British actor known for his roles in television series like "W1A" and "Fleabag" and films such as "Mamma Mia! Here We Go Again."
-
B.
Christopher Smith
Christopher Smith is a relative of English actor Jeremy Irvine, known for his role in the film "War Horse."
-
C.
Christopher Smith
Christopher Smith is an actor known for his performance in the film "Feel Good."
-
D.
Christopher Smith
Christopher Smith is an individual associated with online communities or organizations connected to the Internet.
-
E.
Matthew Fuller
Matthew Fuller was a 17th-century colonial physician and military officer in Plymouth Colony, known as the son of Mayflower passenger Edward Fuller.
- 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_69d822dffc3c8190aa173b90761bffda |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb4a7c8fc81909d10c1f563d7d1e7 |
completed | April 14, 2026, 9:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fda92c25ac8190ba931c009e7ace19 |
completed | May 8, 2026, 9:13 a.m. |
Created at: April 10, 2026, 1:26 a.m.