Triple
T31719715
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Celeste Ackelson |
E809538
|
entity |
| Predicate | spouseOfCharacterPortrayer |
P192842
|
FINISHED |
| Object | Kevin Malone (character from The Office U.S.) |
—
|
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: Kevin Malone (character from The Office U.S.) | Statement: [Celeste Ackelson, spouseOfCharacterPortrayer, Kevin Malone (character from The Office U.S.)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spouseOfCharacterPortrayer Context triple: [Celeste Ackelson, spouseOfCharacterPortrayer, Kevin Malone (character from The Office U.S.)]
-
A.
spouseCharacterOf
Indicates a marital relationship where one character is the spouse of another character.
-
B.
spouseCharacterPlayed
chosen
Indicates that one entity is the spouse of the character portrayed by another entity.
-
C.
portrayedBySpouseOf
Indicates that something is portrayed or depicted by the spouse of a given entity.
-
D.
spouseOfProtagonistOf
Indicates that one entity is the spouse (married partner) of the main character (protagonist) of another entity, typically a narrative work.
-
E.
spouseOfRole
Indicates that one role is the spouse (husband, wife, or equivalent marital partner) of another role.
- 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_69f348e009c8819095d77df52c645b9c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fd6a1c1c4881908090053bc359b181 |
completed | May 8, 2026, 4:44 a.m. |
| PD | Predicate disambiguation | batch_69fd696f24d8819091033afacbdaadc5 |
completed | May 8, 2026, 4:41 a.m. |
Created at: April 30, 2026, 11:18 p.m.