Triple
T1518482
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frozen |
E32172
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object |
Anna
Anna is a spirited and optimistic princess from Disney's animated film "Frozen," known for her bravery, loyalty, and deep love for her sister Elsa.
|
E198466
|
NE FINISHED |
How this triple was built (4 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: Anna | Statement: [Frozen, mainCharacter, Anna]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Anna Context triple: [Frozen, mainCharacter, Anna]
-
A.
Anna
Anna is the given first name of Eleanor Roosevelt, the influential former First Lady of the United States and human rights advocate.
-
B.
Anna
Anna is the given name of Anna Murray Douglass, an African American abolitionist and the first wife of Frederick Douglass.
-
C.
Anna
Anna is a central female character in the comedy Western film "A Million Ways to Die in the West," portrayed as a sharp-shooting, quick-witted woman who helps the protagonist toughen up in the dangerous frontier.
-
D.
Anna
Anna was Empress of Russia from 1730 to 1740, known for her autocratic rule and the dominance of her German favorites at court.
-
E.
Anna
Anna is the given name of pioneering Chinese American actress Anna May Wong, a trailblazing early Hollywood star and fashion icon.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Anna Triple: [Frozen, mainCharacter, Anna]
Generated description
Anna is a spirited and optimistic princess from Disney's animated film "Frozen," known for her bravery, loyalty, and deep love for her sister Elsa.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Anna Target entity description: Anna is a spirited and optimistic princess from Disney's animated film "Frozen," known for her bravery, loyalty, and deep love for her sister Elsa.
-
A.
Anna
Anna is a central female character in the comedy Western film "A Million Ways to Die in the West," portrayed as a sharp-shooting, quick-witted woman who helps the protagonist toughen up in the dangerous frontier.
-
B.
Anna
Anna is a character from the video game "Surfacing," likely serving as a key figure in the game's narrative or player interactions.
-
C.
Anna
Anna is the given first name of Eleanor Roosevelt, the influential former First Lady of the United States and human rights advocate.
-
D.
Anna
Anna is a feminine given name of Hebrew origin meaning "grace" or "favor," widely used across many cultures and languages.
-
E.
Anna
Anna was Empress of Russia from 1730 to 1740, known for her autocratic rule and the dominance of her German favorites at court.
- F. None of above. chosen
Provenance (5 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_69a885e8caf88190a5fbb6159ce87786 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a907ed44ac8190953e428c831e24df |
completed | March 5, 2026, 4:34 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ada967e01481908802baf2de7ad6a7 |
completed | March 8, 2026, 4:52 p.m. |
| NEDg | Description generation | batch_69adab31c0148190bb2f6d1a8e01d942 |
completed | March 8, 2026, 5 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69adae9fdd3081908b1d9d7335cab1bd |
completed | March 8, 2026, 5:15 p.m. |
Created at: March 4, 2026, 7:26 p.m.