Triple
T19619865
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bergens |
E470972
|
entity |
| Predicate | eventInTrolls |
P19113
|
FINISHED |
| Object | lose access to trolls after their escape |
—
|
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: lose access to trolls after their escape | Statement: [Bergens, eventInTrolls, lose access to trolls after their escape]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eventInTrolls Context triple: [Bergens, eventInTrolls, lose access to trolls after their escape]
-
A.
eventIn
chosen
Indicates that an event occurs within, or is situated in, a specific location, context, or larger event.
-
B.
event
Indicates that there exists an occurrence or happening involving one or more entities, typically situated in time and possibly space.
-
C.
eventName
Indicates the specific label or title assigned to identify an event within a system or context.
-
D.
featuresEvent
Indicates that an entity includes, presents, or highlights a particular event as part of its content or offering.
-
E.
eventDescription
Indicates that a textual summary or explanation is provided describing what happens in the event.
- 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_69d8e510fa248190b7afb274a1d4cf73 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e640e512d08190a76bf81b3282e0e5 |
completed | April 20, 2026, 3:06 p.m. |
| PD | Predicate disambiguation | batch_69e514e5cb108190ae260e466c447314 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:43 p.m.