Triple
T17312024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Christmas (town) |
E420321
|
entity |
| Predicate | hasInUniverseTimeSpan |
P82593
|
FINISHED |
| Object | centuries-long siege |
—
|
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: centuries-long siege | Statement: [Christmas (town), hasInUniverseTimeSpan, centuries-long siege]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasInUniverseTimeSpan Context triple: [Christmas (town), hasInUniverseTimeSpan, centuries-long siege]
-
A.
appearsInTimePeriod
Indicates that an entity is present, active, or occurs within a specified time period.
-
B.
timeExistence
Indicates the period or duration during which an entity exists or is valid.
-
C.
hasConceptOfTime
Indicates that an entity possesses an understanding or awareness of time as an abstract concept or measurable dimension.
-
D.
inUniverseAge
Indicates the age of an entity as measured within the timeline or continuity of a specific fictional or defined universe.
-
E.
chronologicalRange
chosen
Indicates the temporal span or period over which something occurs, is valid, or is relevant.
- 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_69d889d22b848190a4663d0b8f8f76e7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e439993bac8190a72f6af529bd7cce |
completed | April 19, 2026, 2:10 a.m. |
| PD | Predicate disambiguation | batch_69e3b01b9d1c8190a406dd941c9b11a1 |
completed | April 18, 2026, 4:23 p.m. |
Created at: April 10, 2026, 5:43 a.m.