Triple
T25881076
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unification of Germany |
E652050
|
entity |
| Predicate | locationOfEndEvent |
P187618
|
FINISHED |
| Object | Hall of Mirrors, Palace of Versailles |
—
|
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: Hall of Mirrors, Palace of Versailles | Statement: [Unification of Germany, locationOfEndEvent, Hall of Mirrors, Palace of Versailles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationOfEndEvent Context triple: [Unification of Germany, locationOfEndEvent, Hall of Mirrors, Palace of Versailles]
-
A.
endLocationOfJourney
Indicates the final destination or stopping point reached at the conclusion of a journey or trip.
-
B.
successorEventLocation
Indicates that the location is where the immediately following or next event in a sequence takes place.
-
C.
eventConcludedAtLocation
chosen
Indicates that an event has finished or come to an end at a specific location.
-
D.
endEvent
Indicates that one event or process marks the termination or conclusion of another event or process.
-
E.
locationOfEventDescribed
Indicates that one entity is the place or setting where the event described by another entity occurs.
- 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_69e7ab3b92cc81908febd90317862647 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69fccdd496048190bca801a8a9eecb62 |
completed | May 7, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69fcccee6240819084680887731ff64b |
completed | May 7, 2026, 5:33 p.m. |
Created at: April 22, 2026, 8:16 a.m.