Triple
T38061285
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Arreat |
E950345
|
entity |
| Predicate | finalActLocationOf |
P12513
|
FINISHED |
| Object | Diablo II: Lord of Destruction |
—
|
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: Diablo II: Lord of Destruction | Statement: [Mount Arreat, finalActLocationOf, Diablo II: Lord of Destruction]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: finalActLocationOf Context triple: [Mount Arreat, finalActLocationOf, Diablo II: Lord of Destruction]
-
A.
formerFinishLocation
Indicates that an entity was previously the finish location of an event or activity, but no longer holds that status.
-
B.
finalAct
Indicates that an action or event is the last or concluding act in a sequence or process.
-
C.
finalHomeOf
Indicates that a location is the last or ultimate home, residence, or resting place of an entity.
-
D.
lastLocation
Indicates the most recent known place or position where an entity was located.
-
E.
finalsLocation
chosen
Indicates the place where the final stage or concluding event of something (such as a competition or process) takes place.
- 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_69f76f01e63c819093b6012fc974f35a |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69ff519b65f081909902ba83b775ef85 |
completed | May 9, 2026, 3:24 p.m. |
| PD | Predicate disambiguation | batch_69ff506fccdc8190bd93269589040aed |
completed | May 9, 2026, 3:19 p.m. |
Created at: May 3, 2026, 4:21 p.m.