Triple
T20813349
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Next plc |
E512369
|
entity |
| Predicate | hasDivision |
P35
|
FINISHED |
| Object | Next Directory |
—
|
NE NERFINISHED |
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: Next Directory | Statement: [Next plc, hasDivision, Next Directory]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Next Directory Context triple: [Next plc, hasDivision, Next Directory]
-
A.
Next
Next is a science fiction novel by Michael Crichton that explores the ethical, legal, and commercial implications of genetic engineering and biotechnology.
-
B.
Next
chosen
Next is a major British multinational clothing, footwear, and home products retailer known for its extensive high-street and online presence.
-
C.
Next
Next is an American R&B group best known for their late-1990s and early-2000s hits like "Too Close" and "Wifey."
-
D.
Next
"Next" is a lo-fi, introspective song by American musician Zack Villere, known for its vulnerable lyrics and mellow, experimental production.
-
E.
Next
Next is a 2007 science fiction action film starring Nicolas Cage as a man who can see a few minutes into his own future.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4cd25088190b48ca9700cd24efc |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2d415688190b66adc44d4df9bbb |
completed | April 21, 2026, 12:20 a.m. |
Created at: April 16, 2026, 12:40 p.m.