Triple
T14309613
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donna Murphy |
E354789
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Tangled |
E70009
|
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: Tangled | Statement: [Donna Murphy, notableWork, Tangled]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tangled Context triple: [Donna Murphy, notableWork, Tangled]
-
A.
Tangled
chosen
Tangled is a 2010 Disney animated musical fantasy film that reimagines the Rapunzel fairy tale with a blend of comedy, adventure, and computer-generated animation.
-
B.
Enchanted
Enchanted is a 2007 Disney live-action/animated musical fantasy film that playfully subverts classic fairy-tale tropes as an animated princess is transported into modern-day New York City.
-
C.
Enchanted
"Enchanted" is a popular 1959 doo-wop ballad by The Platters, known for its romantic lyrics and smooth vocal harmonies.
-
D.
Enchanted
"Enchanted" is a fan-favorite ballad by Taylor Swift, celebrated for its romantic, fairy-tale imagery and emotional storytelling on her album *Speak Now*.
-
E.
Enchanted
Enchanted is an episode of the television series "Friday Night Lights," a drama centered on high school football and small-town life in Texas.
- 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_69d8278ed42c8190b9f882dcce611347 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de85b26da48190a96e2f60ace51335 |
completed | April 14, 2026, 6:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd3d2e2444819090252684673ff3df |
completed | May 8, 2026, 1:32 a.m. |
Created at: April 10, 2026, 1:12 a.m.