Triple
T14413645
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Love Lies Bleeding |
E357391
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | Mark Towns |
E857430
|
NE FINISHED |
How this triple was built (2 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: Mark Towns | Statement: [Love Lies Bleeding, editedBy, Mark Towns]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Towns Context triple: [Love Lies Bleeding, editedBy, Mark Towns]
-
A.
Mark Towns
chosen
Mark Towns is an editor known for his work on the film "The Ritual."
-
B.
John Bromfield
John Bromfield was an American film and television actor best known for his rugged leading-man roles in 1950s crime dramas and Westerns.
-
C.
David Drumlin
David Drumlin is a high-ranking government science advisor and political figure in the science fiction film "Contact," often serving as a skeptical foil to the protagonist Ellie Arroway.
-
D.
Clayton Townsend
Clayton Townsend is a film producer known for his work on major Hollywood comedies and dramas, including the hit movie "Bridesmaids."
-
E.
Mark Suter
Mark Suter is a percussionist known for his work in contemporary and world music, including performances with the Silk Road Ensemble.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d82793421c8190861eb0e673b085de |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de90cb3c708190822f5506ebf7ee9d |
completed | April 14, 2026, 7:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd552858208190ba1550e7c1176a2a |
completed | May 8, 2026, 3:14 a.m. |
Created at: April 10, 2026, 1:17 a.m.