Triple
T14800559
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hardhome |
E347898
|
entity |
| Predicate | partOfSeasonStoryArc |
P103369
|
FINISHED |
| Object | Jon Snow’s Lord Commander storyline |
—
|
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: Jon Snow’s Lord Commander storyline | Statement: [Hardhome, partOfSeasonStoryArc, Jon Snow’s Lord Commander storyline]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfSeasonStoryArc Context triple: [Hardhome, partOfSeasonStoryArc, Jon Snow’s Lord Commander storyline]
-
A.
partOfPlot
chosen
Indicates that one event, action, or element is a constituent component within the overall plot of a narrative.
-
B.
notableStoryArc
Indicates that there exists a significant or prominent narrative storyline or plot development involving the subject.
-
C.
firstMajorStoryArc
Indicates that the related entity represents the initial or earliest major story arc associated with another narrative work or series.
-
D.
occurredInSeason
Indicates that an event or occurrence took place during a specific season within a temporal sequence (such as a TV show season or sports season).
-
E.
partOfSeriesOfEvents
Indicates that an event is one element within a larger, ordered sequence of related events.
- 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_69d822ea8b7c819097dfadf3d45545e6 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69decd62c36c81909c2993dc7d1a79ea |
completed | April 14, 2026, 11:27 p.m. |
| PD | Predicate disambiguation | batch_69de8c0ef8a4819092d84478b1f56db1 |
completed | April 14, 2026, 6:48 p.m. |
Created at: April 10, 2026, 1:31 a.m.