Triple
T26877801
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Earl of Ross (jure uxoris, disputed) |
E676801
|
entity |
| Predicate | latinPhraseUsed |
P79823
|
FINISHED |
| Object | jure uxoris |
—
|
LITERAL 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: jure uxoris | Statement: [Earl of Ross (jure uxoris, disputed), latinPhraseUsed, jure uxoris]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: latinPhraseUsed Context triple: [Earl of Ross (jure uxoris, disputed), latinPhraseUsed, jure uxoris]
-
A.
usedPhrase
Indicates that one entity employed or expressed a particular phrase in speech, writing, or another form of communication.
-
B.
symbolicPhrase
Indicates a relationship where one entity is represented or expressed by a symbolic phrase associated with another entity.
-
C.
isUsedInPhrase
chosen
Indicates that something (such as a word, expression, or symbol) appears as a component within a particular phrase.
-
D.
mottoTextLatin
Indicates that the relationship specifies the Latin-language wording of an entity's motto.
-
E.
hasLatinPhraseMeaning
Indicates that one entity is a Latin phrase that expresses the meaning or translation of another entity.
- 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_69eee9bb44988190b6e11652d028bc59 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f61f19a7588190b11555c673bbf6a3 |
completed | May 2, 2026, 3:58 p.m. |
| PD | Predicate disambiguation | batch_69f611ad2eb48190ac1ed0090f13f7a9 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 5:37 a.m.