Triple
T17907816
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mac |
E447746
|
entity |
| Predicate | fullName |
P16
|
FINISHED |
| Object | Mac |
—
|
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: Mac | Statement: [Mac, fullName, Mac]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mac Context triple: [Mac, fullName, Mac]
-
A.
Mac
Mac is Apple’s line of personal computers known for their sleek hardware design and tight integration with the macOS operating system.
-
B.
Mac
Mac is a Gaelic patronymic prefix meaning "son of," commonly used in Scottish and Irish surnames.
-
C.
Mac
Mac is a character portrayed by Michael Badalucco, best known as the endearing and quirky private investigator on the television series "The Practice."
-
D.
Mac
Mac is a masculine given name, often used as a short form or nickname derived from surnames or longer names beginning with "Mac."
-
E.
Mac
Mac is one of the main characters in the stoner comedy film "Mac & Devin Go to High School," portrayed as a laid-back, marijuana-loving student.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69d8b9f6d394819082a6d69fd1e23d2f |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49e9d458881909e35e1c7a6e85436 |
completed | April 19, 2026, 9:21 a.m. |
Created at: April 10, 2026, 10:19 a.m.