Triple
T14507533
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charles Crumb |
E340303
|
entity |
| Predicate | portrayedIn |
P626
|
FINISHED |
| Object | "Crumb" |
E67876
|
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: "Crumb" | Statement: [Charles Crumb, portrayedIn, "Crumb"]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: "Crumb" Context triple: [Charles Crumb, portrayedIn, "Crumb"]
-
A.
Crumb
chosen
Crumb is a 1994 documentary film about underground cartoonist Robert Crumb, directed by Terry Zwigoff.
-
B.
Crumbs Off the Table
"Crumbs Off the Table" is a song by producer and DJ RJD2, known for its soulful, sample-based hip-hop sound.
-
C.
Crumbs from Your Table
"Crumbs from Your Table" is a song by the Irish rock band U2 from their 2004 album *How to Dismantle an Atomic Bomb*, noted for its critique of global inequality and Western complacency.
-
D.
Kid Crumbs
Kid Crumbs is a hip-hop artist known for his guest appearance on the track "Organix."
-
E.
Crumbs
"Crumbs" is a pop single by American singer Rebecca Black, showcasing her evolution from viral teen sensation to more mature, independent artist.
- 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_69d822d9c0408190b9a2b3643e58bb4d |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69de94e40e44819084f323f8f9982b75 |
completed | April 14, 2026, 7:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd6da07ff481909fb2463b0ea92849 |
completed | May 8, 2026, 4:59 a.m. |
Created at: April 10, 2026, 1:21 a.m.