Triple
T14888706
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrew McCarthy |
E359696
|
entity |
| Predicate | memberOf |
P10
|
FINISHED |
| Object | Brat Pack |
E156715
|
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: Brat Pack | Statement: [Andrew McCarthy, memberOf, Brat Pack]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brat Pack Context triple: [Andrew McCarthy, memberOf, Brat Pack]
-
A.
Brat Pack
chosen
The Brat Pack was a group of young Hollywood actors prominently featured in popular 1980s coming-of-age films such as "The Breakfast Club" and "St. Elmo's Fire."
-
B.
Rowdy
Rowdy is the fighting nickname of Ronda Rousey, the trailblazing mixed martial artist and former UFC champion.
-
C.
Rowdy
Rowdy is the aggressive, hard-charging NASCAR driving persona of American stock car racer Kyle Busch.
-
D.
Rowdy
Rowdy is the costumed bird mascot of the NFL’s Dallas Cowboys, known for entertaining fans at games and team events.
-
E.
Brothers
Brothers is a 2009 psychological drama film about a soldier presumed dead in Afghanistan whose return home disrupts his family, starring Tobey Maguire, Jake Gyllenhaal, and Natalie Portman.
- 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_69d827980cbc8190a0c569ae3940a1d9 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69ded5f6cf5c8190b6b28f58fafe5d59 |
completed | April 15, 2026, 12:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe6b5f22c08190a9530cbd78cfc801 |
completed | May 8, 2026, 11:01 p.m. |
Created at: April 10, 2026, 2:09 a.m.