Triple
T33367193
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Granges-Paccot |
E854385
|
entity |
| Predicate | localName_de |
P22792
|
FINISHED |
| Object | Granges-Paccot |
—
|
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: Granges-Paccot | Statement: [Granges-Paccot, localName_de, Granges-Paccot]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: localName_de Context triple: [Granges-Paccot, localName_de, Granges-Paccot]
-
A.
nameInGerman
chosen
Indicates that an entity is known or referred to by a specific name in the German language.
-
B.
localNameInCroatian
Indicates that the specified name is the local or native name of an entity when expressed in the Croatian language.
-
C.
officialNameLocal
Indicates the officially recognized name of an entity as used in the local or native language context.
-
D.
equivalentSurnameInGerman
Indicates that two surnames are equivalent to each other when translated into or represented in the German language.
-
E.
localNameInSlovene
Indicates the name by which something is locally known or referred to in the Slovene language.
- 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_69f3496bda8c8190bfc8fade9d1b791c |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f73ae120bc8190bff94d38d7a7a00d |
completed | May 3, 2026, 12:09 p.m. |
| PD | Predicate disambiguation | batch_69f73a38d0848190aa5139144b8561c6 |
completed | May 3, 2026, 12:06 p.m. |
Created at: May 1, 2026, 1:35 a.m.