Triple
T17921016
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Locked Down |
E448064
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | Locked Down |
—
|
NE NERFINISHED |
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: Locked Down | Statement: [Locked Down, title, Locked Down]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Locked Down Context triple: [Locked Down, title, Locked Down]
-
A.
Locked Down
chosen
"Locked Down" is a 2021 heist-romantic comedy film set during the COVID-19 lockdown, starring Anne Hathaway and Chiwetel Ejiofor.
-
B.
Lockdown
Lockdown is a professional wrestling pay-per-view event produced by Impact Wrestling, traditionally featuring all matches contested inside a steel cage.
-
C.
Lockdown
"Lockdown" is a dystopian crime novel by Scottish author Peter May, set in a pandemic-stricken London under quarantine.
-
D.
Lockdown
Lockdown is a ruthless Cybertronian bounty hunter and the main antagonist in the film "Transformers: Age of Extinction."
-
E.
Cooped Up
"Cooped Up" is a 2022 hip-hop single by Post Malone featuring Roddy Ricch, known for its melodic hooks and introspective lyrics about fame and isolation.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9f6d394819082a6d69fd1e23d2f |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4a30a11748190be41361d108aee58 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 10:20 a.m.