Triple
T9967889
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Todd Phillips |
E195729
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Due Date |
E625304
|
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: Due Date | Statement: [Todd Phillips, directed, Due Date]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Due Date Context triple: [Todd Phillips, directed, Due Date]
-
A.
Due Date
chosen
"Due Date" is a 2010 American road-trip comedy film directed by Todd Phillips and starring Robert Downey Jr. and Zach Galifianakis.
-
B.
Deadline
"Deadline" is a film featuring actress Tammy Blanchard in a prominent role.
-
C.
Deadline
"Deadline" is a classic science fiction short story, best known for its influential early depiction of nuclear weapons and its publication in the magazine Astounding Science Fiction.
-
D.
Date
Date is an HTTP header field that indicates the date and time at which the message was originated, formatted according to internet date/time standards.
-
E.
Date
Date is a Japanese samurai clan name most famously associated with the powerful Sengoku-period warlord Date Masamune.
- 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_69ca82ebd1288190912f9e4482d1fa35 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb71f9d7c8190ac02c53052c1c6ad |
completed | April 2, 2026, 12:23 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d257c002cc8190becc9730b2c01782 |
completed | April 5, 2026, 12:38 p.m. |
Created at: March 30, 2026, 8:47 p.m.