Triple
T3241147
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tarzan (1999 film) |
E67967
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object |
Noni White
Noni White is an American screenwriter best known for co-writing Disney films such as "Newsies" and contributing to the screenplay of the animated feature "Tarzan."
|
E339901
|
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: Noni White | Statement: [Tarzan (1999 film), screenwriter, Noni White]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Noni White Context triple: [Tarzan (1999 film), screenwriter, Noni White]
-
A.
Jadagrace Berry
Jadagrace Berry is an American actress, dancer, and singer best known for her early role in the science fiction film "Terminator Salvation."
-
B.
Nuʻuuli
Nuʻuuli is a village and commercial center on the island of Tutuila in American Samoa.
-
C.
Kali Ngrowo
Kali Ngrowo is a significant river in East Java, Indonesia, known as one of the main waterways feeding the Brantas River system.
-
D.
Nggela Pile
Nggela Pile is one of the principal islands in the Florida Islands group of the Solomon Islands in the South Pacific.
-
E.
Luman Reed
Luman Reed was a prominent 19th-century New York merchant and art patron who played a key role in supporting early American painters, including members of the Hudson River School.
- 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: Noni White Triple: [Tarzan (1999 film), screenwriter, Noni White]
Generated description
Noni White is an American screenwriter best known for co-writing Disney films such as "Newsies" and contributing to the screenplay of the animated feature "Tarzan."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Noni White Target entity description: Noni White is an American screenwriter best known for co-writing Disney films such as "Newsies" and contributing to the screenplay of the animated feature "Tarzan."
-
A.
Jadagrace Berry
Jadagrace Berry is an American actress, dancer, and singer best known for her early role in the science fiction film "Terminator Salvation."
-
B.
Nuʻuuli
Nuʻuuli is a village and commercial center on the island of Tutuila in American Samoa.
-
C.
Kali Ngrowo
Kali Ngrowo is a significant river in East Java, Indonesia, known as one of the main waterways feeding the Brantas River system.
-
D.
Nggela Pile
Nggela Pile is one of the principal islands in the Florida Islands group of the Solomon Islands in the South Pacific.
-
E.
Luman Reed
Luman Reed was a prominent 19th-century New York merchant and art patron who played a key role in supporting early American painters, including members of the Hudson River School.
- 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_69ad858d27348190abb61c280b4c86a9 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaef76d908190815bb456e366ee0a |
completed | March 8, 2026, 5:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b27754492c819099bab9a2a3344561 |
completed | March 12, 2026, 8:20 a.m. |
| NEDg | Description generation | batch_69b27a0c1f74819087bd0aa869eefd7b |
completed | March 12, 2026, 8:32 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b27acca734819083bdd7713b10ff1a |
completed | March 12, 2026, 8:35 a.m. |
Created at: March 8, 2026, 3:08 p.m.