Triple
T12713158
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | House of Griffins |
E303770
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Stettin |
E366687
|
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: Stettin | Statement: [House of Griffins, capital, Stettin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stettin Context triple: [House of Griffins, capital, Stettin]
-
A.
Stettin
chosen
Stettin, now known as Szczecin, is a major port city on the Oder River in northwestern Poland near the Baltic Sea.
-
B.
Breslau
Breslau is the historical German name for the city now known as Wrocław in southwestern Poland, a major cultural and academic center in Central Europe.
-
C.
Danzig
Danzig is an American heavy metal band formed by singer Glenn Danzig, known for its dark, blues-influenced sound and songs like "Mother."
-
D.
Frankfurt (Oder)
Frankfurt (Oder) is a German city on the Oder River at the Polish border, known as a historic university and trade center in the state of Brandenburg.
-
E.
Świdwin
Świdwin is a historic town in northwestern Poland, known for its medieval castle and location in the West Pomeranian Voivodeship.
- 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_69d7bdf084148190ab9d513dc0735af4 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96208fa6481909d6fd43654752a2d |
completed | April 10, 2026, 8:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6cbb4d0088190b71fc0573cd40ddd |
completed | May 3, 2026, 4:14 a.m. |
Created at: April 9, 2026, 5:23 p.m.