Triple
T30167170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | cohors I Aelia Dacorum |
E766826
|
entity |
| Predicate | nameElementRefersTo |
P168512
|
FINISHED |
| Object | imperial family name Aelius |
—
|
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: imperial family name Aelius | Statement: [cohors I Aelia Dacorum, nameElementRefersTo, imperial family name Aelius]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nameElementRefersTo Context triple: [cohors I Aelia Dacorum, nameElementRefersTo, imperial family name Aelius]
-
A.
nameElement
Indicates that one entity serves as the name or label assigned to another entity or element.
-
B.
nameElementIn
Indicates that an entity is (or contains) a specific name element within a larger naming structure or system.
-
C.
nameElement2
Indicates that the second element in a pair or sequence serves as or contains a name associated with the relationship.
-
D.
nameElement1
Indicates that the first element in a pair or structure serves as or contains a name.
-
E.
nameMayReferTo
Indicates that a given name or label can ambiguously denote or be used for one or more possible entities.
- F. None of above. chosen
Provenance (4 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_69f2247a968881909d79c18f2bfcb275 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67f083c208190aa0ead76cb6ced98 |
completed | May 2, 2026, 10:47 p.m. |
| PD | Predicate disambiguation | batch_69f673c7a4588190837854f3ef61e6bf |
completed | May 2, 2026, 9:59 p.m. |
| PDg | Predicate description generation | batch_69f6749f205c81909d1aacf462912eee |
completed | May 2, 2026, 10:03 p.m. |
Created at: April 29, 2026, 7:23 p.m.