Triple
T11543978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deckard Cain |
E273736
|
entity |
| Predicate | homeLocation |
P75
|
FINISHED |
| Object | New Tristram |
E273729
|
NE 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: New Tristram | Statement: [Deckard Cain, homeLocation, New Tristram]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: New Tristram Context triple: [Deckard Cain, homeLocation, New Tristram]
-
A.
Tristram
Tristram is the full given name of Tris Speaker, a Hall of Fame Major League Baseball outfielder widely regarded as one of the greatest defensive center fielders in history.
-
B.
Tristram
Tristram is a narrative poem by Edwin Arlington Robinson that reimagines the Arthurian legend of Tristan and Iseult.
-
C.
Tristram
chosen
Tristram is a dark, demon-plagued town in Blizzard's Diablo series, serving as one of its most iconic and tragic settings.
-
D.
Rocherath
Rocherath is a village in eastern Belgium, close to the German border, known for its location near key World War II Battle of the Bulge sites.
-
E.
Mainbernheim
Mainbernheim is a small historic town in the Franconian wine-growing region of northern Bavaria, Germany.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6aae4dfa48190a3ab0b19a159a3c5 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d886e1d754819089f3b6be3404fa0b |
completed | April 10, 2026, 5:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e6e82153f48190ae64146d7f28b780 |
completed | April 21, 2026, 2:59 a.m. |
Created at: April 8, 2026, 9:37 p.m.