Triple
T36341838
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Who (Sunny song) |
E894944
|
entity |
| Predicate | hasFirstLetterOfTitle |
P27166
|
FINISHED |
| Object | W |
—
|
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: W | Statement: [Who (Sunny song), hasFirstLetterOfTitle, W]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFirstLetterOfTitle Context triple: [Who (Sunny song), hasFirstLetterOfTitle, W]
-
A.
hasTitleLetter
Indicates that an entity possesses a specific letter or character within its title.
-
B.
hasTitleCasing
Indicates that a text string is formatted in title case, with the principal words capitalized according to title-casing conventions.
-
C.
hasInitialLetters
chosen
Indicates that one entity’s initial letters or acronym are derived from or correspond to the other entity.
-
D.
hasTitleCharacterFrom
Indicates that a work has a title that includes or is derived from a specific character.
-
E.
isCapitalised
Indicates that a given string or word is written with its first letter in uppercase (and the rest in lowercase, if applicable).
- 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_69f76e4e90148190b02fe52593c70b5b |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a000efe971081909de03f875a7ad6cc |
completed | May 10, 2026, 4:52 a.m. |
| PD | Predicate disambiguation | batch_6a000c4ffe788190a5757af60aadd9f3 |
completed | May 10, 2026, 4:40 a.m. |
Created at: May 3, 2026, 4:09 p.m.