Triple
T27874891
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ghost of Christmas Present |
E704899
|
entity |
| Predicate | lifespanWithinStory |
P44224
|
FINISHED |
| Object | one day |
—
|
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: one day | Statement: [Ghost of Christmas Present, lifespanWithinStory, one day]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lifespanWithinStory Context triple: [Ghost of Christmas Present, lifespanWithinStory, one day]
-
A.
followsLifeSpanOfCharacters
Indicates that one entity’s timeline or progression is structured to track or mirror the life spans of specified characters.
-
B.
yearsActiveInStory
Indicates the span of years during which the entity is active or participates within the context of the story.
-
C.
narrativeTimeSpanHours
chosen
Indicates the duration of a narrative or story event measured in hours.
-
D.
timeOfNarrative
Indicates the specific time or period during which the events of a narrative are set or unfold.
-
E.
lifespanType
Indicates the type or category of lifespan associated with an entity, such as whether it is finite, indefinite, or of a particular defined duration.
- 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_69ef84111bb4819084298f994b31c62f |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f6397e95908190bae6cfcd65e3fc20 |
completed | May 2, 2026, 5:50 p.m. |
| PD | Predicate disambiguation | batch_69f6318be69481909d1bcf29b7b60eb2 |
completed | May 2, 2026, 5:17 p.m. |
Created at: April 27, 2026, 6:26 p.m.