Triple
T3016059
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dr. Cyclops |
E82337
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object |
Thomas Coley
Thomas Coley was an American actor best known for his role in the 1940 science fiction horror film "Dr. Cyclops."
|
E344711
|
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: Thomas Coley | Statement: [Dr. Cyclops, castMember, Thomas Coley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thomas Coley Context triple: [Dr. Cyclops, castMember, Thomas Coley]
-
A.
George C. Perkins
George C. Perkins was an American politician and businessman who served as the 14th governor of California and later as a U.S. Senator.
-
B.
George A. Perkins
George A. Perkins was an American lawyer best known as a founding partner of the prominent U.S. law firm Perkins Coie.
-
C.
William Burnet Tuthill
William Burnet Tuthill was an American architect best known for designing New York City's renowned concert venue Carnegie Hall.
-
D.
Joseph Twichell
Joseph Twichell was a 19th-century American Congregational minister and close friend and advisor to author Mark Twain.
-
E.
Edward Mills
Edward Mills was a British architect known for designing the International Maritime Organization (IMO) Headquarters in London.
- 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: Thomas Coley Triple: [Dr. Cyclops, castMember, Thomas Coley]
Generated description
Thomas Coley was an American actor best known for his role in the 1940 science fiction horror film "Dr. Cyclops."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Thomas Coley Target entity description: Thomas Coley was an American actor best known for his role in the 1940 science fiction horror film "Dr. Cyclops."
-
A.
George C. Perkins
George C. Perkins was an American politician and businessman who served as the 14th governor of California and later as a U.S. Senator.
-
B.
George A. Perkins
George A. Perkins was an American lawyer best known as a founding partner of the prominent U.S. law firm Perkins Coie.
-
C.
William Burnet Tuthill
William Burnet Tuthill was an American architect best known for designing New York City's renowned concert venue Carnegie Hall.
-
D.
Joseph Twichell
Joseph Twichell was a 19th-century American Congregational minister and close friend and advisor to author Mark Twain.
-
E.
Edward Mills
Edward Mills was a British architect known for designing the International Maritime Organization (IMO) Headquarters in London.
- 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_69ad8b1eb53481908c39bbcd1ec104b2 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9a6b37288190a6965d183ca4b08b |
completed | March 8, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b2e81339d08190aa74556cc68fba20 |
completed | March 12, 2026, 4:21 p.m. |
| NEDg | Description generation | batch_69b2ec2d96cc8190987d4dff1515384e |
completed | March 12, 2026, 4:39 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b2ecdecb6481908c7af9d6925f6e53 |
completed | March 12, 2026, 4:42 p.m. |
Created at: March 8, 2026, 3 p.m.