Triple
T3078546
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2018 NWSL Championship |
E64198
|
entity |
| Predicate | coachOfLosingTeam |
P21416
|
FINISHED |
| Object | Mark Parsons |
E59776
|
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 Parsons | Statement: [2018 NWSL Championship, coachOfLosingTeam, Mark Parsons]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Parsons Context triple: [2018 NWSL Championship, coachOfLosingTeam, Mark Parsons]
-
A.
Mark Parsons
chosen
Mark Parsons is an English football manager best known for his successful tenure leading the Portland Thorns FC in the National Women's Soccer League.
-
B.
David Burrows
David Burrows is a film editor best known for his work on major animated features, including The Lego Movie.
-
C.
Charlie Parsons
Charlie Parsons is a British television producer best known for creating the pioneering reality competition show "Survivor."
-
D.
Jon Plowman
Jon Plowman is a British television producer best known for his influential work on BBC comedies, including series such as Absolutely Fabulous and The Office.
-
E.
Mel Hunter
Mel Hunter was an American illustrator and artist best known for his science fiction book and magazine covers in the mid-20th century.
- 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_69ad857bb4c88190a4cf27893fcabed8 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada1a86a848190a47ca127cc7e6326 |
completed | March 8, 2026, 4:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b1f890a21c8190bcb78fe5c9ec6e75 |
completed | March 11, 2026, 11:19 p.m. |
Created at: March 8, 2026, 3:02 p.m.