Triple
T15908062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ron Underwood |
E385772
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Speechless |
E664938
|
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: Speechless | Statement: [Ron Underwood, directed, Speechless]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Speechless Context triple: [Ron Underwood, directed, Speechless]
-
A.
Speechless
"Speechless" is a powerful ballad performed by Princess Jasmine in Disney's 2019 live-action adaptation of Aladdin, expressing her determination to speak out and claim her agency.
-
B.
Speechless
"Speechless" is a romantic R&B ballad by Beyoncé featured on her debut solo album, Dangerously in Love.
-
C.
Speechless
"Speechless" is a popular country-pop ballad by American duo Dan + Shay, widely recognized for its romantic theme and strong chart performance.
-
D.
Speechless
chosen
"Speechless" is a 1994 romantic comedy film about two rival political speechwriters who fall in love during a heated election campaign.
-
E.
Unspoken
Unspoken is a song by American singer-songwriter Matt Morris, known for its introspective lyrics and soulful pop style.
- 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_69d86da686e4819097cbf3b1fc2d881d |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1565c11bc819091b1fd85901a832d |
completed | April 16, 2026, 9:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb055307081908a13c98a0e16780c |
completed | May 9, 2026, 10:08 p.m. |
Created at: April 10, 2026, 4:52 a.m.