Triple
T8966191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ernie Sabella |
E214138
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Mouse Hunt |
E295947
|
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: Mouse Hunt | Statement: [Ernie Sabella, notableWork, Mouse Hunt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mouse Hunt Context triple: [Ernie Sabella, notableWork, Mouse Hunt]
-
A.
Hunt
Hunt is a common English surname borne by numerous notable figures across fields such as architecture, politics, sports, and the arts.
-
B.
Hunt
Hunt is a South Korean espionage action thriller film directed by and starring Lee Jung-jae, centered on two rival intelligence agents uncovering a massive political conspiracy.
-
C.
MouseHunt (1997 film)
chosen
MouseHunt (1997 film) is a 1997 slapstick comedy film starring Nathan Lane and Lee Evans as hapless brothers battling a clever mouse in a dilapidated mansion they hope to restore and sell.
-
D.
Monster Hunt
Monster Hunt is a popular Chinese fantasy-comedy film that blends live-action and CGI to tell a whimsical story about humans and monsters coexisting.
-
E.
Kodos
Kodos is a recurring alien character from the animated television series "The Simpsons," often appearing in the show's "Treehouse of Horror" Halloween episodes.
- 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_69ca839cd6008190a1546a701a56710c |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc67623818819096aee155a9b43e8f |
completed | April 1, 2026, 12:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfc95879c08190b0091548c8c00207 |
completed | April 3, 2026, 2:06 p.m. |
Created at: March 30, 2026, 7:01 p.m.