Triple
T34425897
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tamzin |
E883665
|
entity |
| Predicate | differsFromTamsinBy |
P61682
|
FINISHED |
| Object | use of letter z instead of s |
—
|
LITERAL 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: use of letter z instead of s | Statement: [Tamzin, differsFromTamsinBy, use of letter z instead of s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: differsFromTamsinBy Context triple: [Tamzin, differsFromTamsinBy, use of letter z instead of s]
-
A.
nameContrastsWith
Indicates that one name is deliberately chosen or used to highlight a difference or opposition in meaning, style, or identity relative to another name.
-
B.
hasDifferentPersonalityIn
Indicates that an entity exhibits a different personality or character traits within a specified context, setting, or situation.
-
C.
differIn
chosen
Indicates that two entities are not the same in at least one specified aspect, attribute, or value.
-
D.
hasDistinctPronounsFrom
Indicates that two entities use different sets of pronouns from each other.
-
E.
isTaylor’sVersion
Indicates that a musical work is the re-recorded “Taylor’s Version” of an original release by Taylor Swift.
- F. None of above.
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_69f349c3dd2c819092cc9e64809f4a42 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f727bde8f88190ad746ca515134ca1 |
completed | May 3, 2026, 10:47 a.m. |
| PD | Predicate disambiguation | batch_69f72739c30c81908642eef3feb3afcf |
completed | May 3, 2026, 10:45 a.m. |
Created at: May 1, 2026, 2 a.m.