Triple
T4868806
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Jane's Last Dance |
E109035
|
entity |
| Predicate | musicVideoDirector |
P4911
|
FINISHED |
| Object |
Keir McFarlane
Keir McFarlane is a music video director best known for his work on high-profile rock videos in the 1990s.
|
E477256
|
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: Keir McFarlane | Statement: [Mary Jane's Last Dance, musicVideoDirector, Keir McFarlane]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Keir McFarlane Context triple: [Mary Jane's Last Dance, musicVideoDirector, Keir McFarlane]
-
A.
Neil MacLeod
Neil MacLeod is a personal name shared by several notable individuals, including figures in politics, sports, and the arts.
-
B.
Duncan MacMillan
Duncan MacMillan is an American businessman best known as one of the co-founders of the global financial information and media company Bloomberg L.P.
-
C.
Duncan MacMillan
Duncan MacMillan is an American businessman best known as a co-founder of Interactive Data Corporation, a major provider of financial market data and analytics.
-
D.
Brian MacDevitt
Brian MacDevitt is a Tony Award–winning American lighting designer renowned for his work on numerous high-profile Broadway productions.
-
E.
Iain McCrory
Iain McCrory is the father of the late British actress Helen McCrory, known for her acclaimed work in film, television, and theatre.
- 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: Keir McFarlane Triple: [Mary Jane's Last Dance, musicVideoDirector, Keir McFarlane]
Generated description
Keir McFarlane is a music video director best known for his work on high-profile rock videos in the 1990s.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Keir McFarlane Target entity description: Keir McFarlane is a music video director best known for his work on high-profile rock videos in the 1990s.
-
A.
Neil MacLeod
Neil MacLeod is a personal name shared by several notable individuals, including figures in politics, sports, and the arts.
-
B.
Duncan MacMillan
Duncan MacMillan is an American businessman best known as one of the co-founders of the global financial information and media company Bloomberg L.P.
-
C.
Duncan MacMillan
Duncan MacMillan is an American businessman best known as a co-founder of Interactive Data Corporation, a major provider of financial market data and analytics.
-
D.
Brian MacDevitt
Brian MacDevitt is a Tony Award–winning American lighting designer renowned for his work on numerous high-profile Broadway productions.
-
E.
Iain McCrory
Iain McCrory is the father of the late British actress Helen McCrory, known for her acclaimed work in film, television, and theatre.
- 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_69bd440d96a48190b0c87069adef2af1 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6d7d809081909fc7c80c56f72840 |
completed | March 20, 2026, 3:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be67ea7cd88190b89f5cc1d85c1994 |
completed | March 21, 2026, 9:42 a.m. |
| NEDg | Description generation | batch_69be6a22858081909be389f3d40e518c |
completed | March 21, 2026, 9:51 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69be6a8131ec8190bf9ccf3eea10ce83 |
completed | March 21, 2026, 9:53 a.m. |
Created at: March 20, 2026, 1:27 p.m.