Triple
T9988237
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Lynch |
E196821
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Lynch |
E312013
|
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: Lynch | Statement: [David Lynch, familyName, Lynch]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lynch Context triple: [David Lynch, familyName, Lynch]
-
A.
Lynch
chosen
Lynch is a common Irish surname historically associated with one of the prominent merchant families of Galway and now borne by people worldwide.
-
B.
Lehane
Lehane is the surname of Dennis Lehane, an American novelist known for his crime and mystery fiction, including works like "Mystic River" and the Kenzie-Gennaro series.
-
C.
Nightcrawler
Nightcrawler is a blue-skinned, teleporting mutant superhero from Marvel's X-Men, known for his acrobatic skills, prehensile tail, and strong Catholic faith.
-
D.
Nightcrawler
Nightcrawler is a 2014 neo-noir thriller film starring Jake Gyllenhaal as an amoral crime videographer prowling Los Angeles for sensational footage.
-
E.
Dakiti
"Dakiti" is a globally popular reggaeton track by Puerto Rican artist Bad Bunny, known for its smooth, atmospheric production and chart-topping success.
- 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_69ca82f1678c819093d06320a05f16a4 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdc79e10408190bcb4e55b6a0df79c |
completed | April 2, 2026, 1:34 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d25810584c81908382cf6edd700530 |
completed | April 5, 2026, 12:39 p.m. |
Created at: March 30, 2026, 8:50 p.m.