Triple
T621472
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Curran |
E14522
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Tracks |
E62101
|
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: Tracks | Statement: [John Curran, notableWork, Tracks]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tracks Context triple: [John Curran, notableWork, Tracks]
-
A.
Tracks
chosen
Tracks is a 2013 biographical drama film chronicling Robyn Davidson’s 1,700-mile trek across the Australian desert, produced by Iain Canning.
-
B.
Tunes
Tunes is a town in Portugal’s Algarve region known as a key railway junction linking major lines in the south of the country.
-
C.
Songs Cycled
Songs Cycled is a 2013 studio album by American composer and arranger Van Dyke Parks that revisits and reimagines his eclectic songwriting across new and previously released material.
-
D.
Test Track
Test Track is a high-speed automotive-themed attraction at EPCOT where guests experience a simulated vehicle testing facility.
-
E.
Singel
Singel is a historic canal in Amsterdam that once served as the city’s medieval moat and now forms part of its iconic canal belt.
- 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_69a4934b17c881909ace8270e8ddd202 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49e3e5d80819096e72e11b533f931 |
completed | March 1, 2026, 8:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a563cab73c819082b51d64d249143b |
completed | March 2, 2026, 10:17 a.m. |
Created at: March 1, 2026, 7:35 p.m.