Triple
T22021964
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barkskins |
E543866
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object |
Tallulah Haddon
Tallulah Haddon is a British actress known for her roles in television dramas such as "Kiss Me First" and "Taboo."
|
E1514110
|
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: Tallulah Haddon | Statement: [Barkskins, stars, Tallulah Haddon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tallulah Haddon Context triple: [Barkskins, stars, Tallulah Haddon]
-
A.
Tallulah Winters
Tallulah Winters is a fictional character appearing in the Doctor Who audio drama "Ship Ahoy."
-
B.
Hanna McDodd
Hanna McDodd is a character from Dr. Seuss’s "Horton Hears a Who!" universe, depicted as one of Mayor Ned McDodd’s many children in Whoville.
-
C.
Lucetta Creeson
Lucetta Creeson is a fictional character appearing in the narrative of the work titled "Stone."
-
D.
Daisy Suckley
Daisy Suckley was a close confidante and distant cousin of U.S. President Franklin D. Roosevelt, known for her intimate correspondence with him and her connection to the Wilderstein estate in New York.
-
E.
Tallulah Hoffman
Tallulah Hoffman is the daughter of theater director and producer Mimi O'Donnell and the late actor Philip Seymour Hoffman.
- 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: Tallulah Haddon Triple: [Barkskins, stars, Tallulah Haddon]
Generated description
Tallulah Haddon is a British actress known for her roles in television dramas such as "Kiss Me First" and "Taboo."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tallulah Haddon Target entity description: Tallulah Haddon is a British actress known for her roles in television dramas such as "Kiss Me First" and "Taboo."
-
A.
Tallulah Winters
Tallulah Winters is a fictional character appearing in the Doctor Who audio drama "Ship Ahoy."
-
B.
Hanna McDodd
Hanna McDodd is a character from Dr. Seuss’s "Horton Hears a Who!" universe, depicted as one of Mayor Ned McDodd’s many children in Whoville.
-
C.
Lucetta Creeson
Lucetta Creeson is a fictional character appearing in the narrative of the work titled "Stone."
-
D.
Daisy Suckley
Daisy Suckley was a close confidante and distant cousin of U.S. President Franklin D. Roosevelt, known for her intimate correspondence with him and her connection to the Wilderstein estate in New York.
-
E.
Tallulah Hoffman
Tallulah Hoffman is the daughter of theater director and producer Mimi O'Donnell and the late actor Philip Seymour Hoffman.
- 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_69e11e2e8ea4819084210fe06d3a1b8d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127c8ac6881909a9e96e0873a3ae2 |
completed | April 28, 2026, 9:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a738527b481908b8f5aeb7d4cf5c7 |
completed | May 18, 2026, 2:03 a.m. |
| NEDg | Description generation | batch_6a0a745e534881909a681b9f2234afa5 |
completed | May 18, 2026, 2:07 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a7857e6dc819088b592cdff7d4cf3 |
completed | May 18, 2026, 2:24 a.m. |
Created at: April 16, 2026, 8:23 p.m.