Triple
T23070731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Sinatra as Dave Hirsh |
E575185
|
entity |
| Predicate | characterReturnsTo |
P140199
|
FINISHED |
| Object | small hometown |
—
|
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: small hometown | Statement: [Frank Sinatra as Dave Hirsh, characterReturnsTo, small hometown]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterReturnsTo Context triple: [Frank Sinatra as Dave Hirsh, characterReturnsTo, small hometown]
-
A.
revisitsCharacterFrom
Indicates that a work, scene, or narrative element returns to and features a character who has appeared previously.
-
B.
intendedReturnOfCharacter
chosen
Indicates that one entity is the planned or expected destination, place, or state to which a character is meant to return.
-
C.
reappearanceEpisode
Indicates the episode in which an entity that has appeared before returns or shows up again.
-
D.
marksReturnOfActorAsCharacter
Indicates that an instance marks the return of an actor portraying a particular character after a period of absence.
-
E.
isRecurringCharacter
Indicates that an entity appears repeatedly or regularly within a given narrative, series, or context rather than only once.
- 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_69e245bd6e4c8190bb8942245b68cad5 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18c5f17348190ab92cfdae9bcaeba |
completed | April 29, 2026, 4:43 a.m. |
| PD | Predicate disambiguation | batch_69ef89d5f71881908b9f9d0c8aab278c |
completed | April 27, 2026, 4:07 p.m. |
Created at: April 17, 2026, 3:56 p.m.