Triple
T35152875
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sack of King's Landing |
E1015040
|
entity |
| Predicate | occursNearEndOf |
P120372
|
FINISHED |
| Object | Robert's Rebellion |
—
|
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: Robert's Rebellion | Statement: [Sack of King's Landing, occursNearEndOf, Robert's Rebellion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: occursNearEndOf Context triple: [Sack of King's Landing, occursNearEndOf, Robert's Rebellion]
-
A.
occursNear
Indicates that one event or entity takes place or exists in close spatial proximity to another.
-
B.
nearFinishOf
chosen
Indicates that one entity is located close to the endpoint or finishing section of another entity.
-
C.
occupiesEnd
Indicates that one entity takes place at, or extends up to, the ending point or final position of another entity or interval.
-
D.
assembledNearEndOf
Indicates that one entity is put together or constructed in close proximity to the endpoint or final section of another entity.
-
E.
endOf
Indicates that one entity marks the terminating point or final boundary of another entity, event, or interval.
- 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_69f76ddb3a708190b521ba2970b17178 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f78cefb12c8190a955da746e14799f |
completed | May 3, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69f78b9106008190930b3b3675b737d6 |
completed | May 3, 2026, 5:53 p.m. |
Created at: May 3, 2026, 4:02 p.m.