Triple
T24640799
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Laura García |
E609954
|
entity |
| Predicate | componentFamilyNameOrigin |
P3325
|
FINISHED |
| Object | García is of Iberian origin |
—
|
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: García is of Iberian origin | Statement: [Laura García, componentFamilyNameOrigin, García is of Iberian origin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: componentFamilyNameOrigin Context triple: [Laura García, componentFamilyNameOrigin, García is of Iberian origin]
-
A.
componentFamilyName
Indicates the family or group designation to which a given component belongs.
-
B.
isOriginalFamilyNameOf
Indicates that a given family name is the original or birth surname of a person, from which any later or changed surnames may have derived.
-
C.
hasNameOrigin
chosen
Indicates that the origin or source of an entity’s name is specified by the related entity.
-
D.
featuresFamilyName
Indicates that an entity is associated with or displays a particular family name.
-
E.
hasNameOriginType
Indicates that there is a specific type or category describing the origin of an entity’s name.
- 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_69e2c4d28f848190ac38c400060e943d |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f2be064ff88190b5d9e5ec75a41242 |
completed | April 30, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f2a6d0ab708190b2e3b94dd20ca76b |
completed | April 30, 2026, 12:48 a.m. |
Created at: April 18, 2026, 2:33 a.m.