Triple
T21095764
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Waterloo Road |
E519760
|
entity |
| Predicate | hasMainCharacter |
P1183
|
FINISHED |
| Object |
Kym Kelly
Kym Kelly is a fictional character from the British television drama series "Waterloo Road."
|
E1466666
|
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: Kym Kelly | Statement: [Waterloo Road, hasMainCharacter, Kym Kelly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kym Kelly Context triple: [Waterloo Road, hasMainCharacter, Kym Kelly]
-
A.
Kym Lucas
Kym Lucas is an American Episcopal bishop who serves as the diocesan leader of the Episcopal Diocese of Colorado.
-
B.
Kym Johnson
Kym Johnson is an Australian professional ballroom dancer and choreographer best known for her long-running role as a pro on the U.S. television show "Dancing with the Stars."
-
C.
Carol Kelly
Carol Kelly is an American actress best known for her role in the 1958 Western film "Terror in a Texas Town."
-
D.
Kylie Rogers
Kylie Rogers is an American actress best known for her lead role as the young girl in the faith-based drama film "Miracles from Heaven."
-
E.
Leanne Lyons
Leanne Lyons is an American R&B singer best known as a founding member of the 1990s girl group SWV (Sisters With Voices).
- 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: Kym Kelly Triple: [Waterloo Road, hasMainCharacter, Kym Kelly]
Generated description
Kym Kelly is a fictional character from the British television drama series "Waterloo Road."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kym Kelly Target entity description: Kym Kelly is a fictional character from the British television drama series "Waterloo Road."
-
A.
Kym Lucas
Kym Lucas is an American Episcopal bishop who serves as the diocesan leader of the Episcopal Diocese of Colorado.
-
B.
Kym Johnson
Kym Johnson is an Australian professional ballroom dancer and choreographer best known for her long-running role as a pro on the U.S. television show "Dancing with the Stars."
-
C.
Carol Kelly
Carol Kelly is an American actress best known for her role in the 1958 Western film "Terror in a Texas Town."
-
D.
Kylie Rogers
Kylie Rogers is an American actress best known for her lead role as the young girl in the faith-based drama film "Miracles from Heaven."
-
E.
Leanne Lyons
Leanne Lyons is an American R&B singer best known as a founding member of the 1990s girl group SWV (Sisters With Voices).
- 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_69e0b508d8dc81909be940dafe36c8f7 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e71b5845f88190a16f3df157f0906c |
completed | April 21, 2026, 6:38 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a095a5e7f048190b485f392105666d2 |
completed | May 17, 2026, 6:04 a.m. |
| NEDg | Description generation | batch_6a095b6d25f8819097334c13ef37003e |
completed | May 17, 2026, 6:08 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a095c7c8840819087c9860a75314b83 |
completed | May 17, 2026, 6:13 a.m. |
Created at: April 16, 2026, 2:52 p.m.