Triple
T18056138
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Twin Town |
E432043
|
entity |
| Predicate | featuresCharacter |
P626
|
FINISHED |
| Object |
Julian Lewis
Julian Lewis is a character from the British television drama series "Twin Town."
|
E1303937
|
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: Julian Lewis | Statement: [Twin Town, featuresCharacter, Julian Lewis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Julian Lewis Context triple: [Twin Town, featuresCharacter, Julian Lewis]
-
A.
Julian Lewis
Julian Lewis is a developmental biologist best known as a co-author of the influential textbook "Molecular Biology of the Cell."
-
B.
Julian Reid
Julian Reid is a relatively obscure individual whose specific public notability is not clearly established from the available information.
-
C.
Julian Dennison
Julian Dennison is a New Zealand actor best known for his breakout role in "Hunt for the Wilderpeople" and his performance in "Deadpool 2."
-
D.
Julian Cress
Julian Cress is an Australian television producer best known for co-creating and producing the popular reality renovation series "The Block."
-
E.
Julian Richards
Julian Richards is a British film director and screenwriter known for his work in independent horror and thriller cinema.
- 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: Julian Lewis Triple: [Twin Town, featuresCharacter, Julian Lewis]
Generated description
Julian Lewis is a character from the British television drama series "Twin Town."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Julian Lewis Target entity description: Julian Lewis is a character from the British television drama series "Twin Town."
-
A.
Julian Lewis
Julian Lewis is a developmental biologist best known as a co-author of the influential textbook "Molecular Biology of the Cell."
-
B.
Julian Reid
Julian Reid is a relatively obscure individual whose specific public notability is not clearly established from the available information.
-
C.
Julian Dennison
Julian Dennison is a New Zealand actor best known for his breakout role in "Hunt for the Wilderpeople" and his performance in "Deadpool 2."
-
D.
Julian Cress
Julian Cress is an Australian television producer best known for co-creating and producing the popular reality renovation series "The Block."
-
E.
Julian Richards
Julian Richards is a British film director and screenwriter known for his work in independent horror and thriller cinema.
- 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_69d8b906482481908183315b9ecf9994 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4c102d08081908d2419c898213400 |
completed | April 19, 2026, 11:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0356674d7c8190ac48575665c2364b |
completed | May 12, 2026, 4:33 p.m. |
| NEDg | Description generation | batch_6a0357eec5b48190b8e8c9fde80dcc65 |
completed | May 12, 2026, 4:40 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a03586945708190ba31099fd01de79b |
completed | May 12, 2026, 4:42 p.m. |
Created at: April 10, 2026, 10:26 a.m.