Triple
T29307254
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint Jovita |
E743128
|
entity |
| Predicate | hasSiblingOrCompanion |
P55387
|
FINISHED |
| Object | Saint Faustinus |
—
|
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: Saint Faustinus | Statement: [Saint Jovita, hasSiblingOrCompanion, Saint Faustinus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSiblingOrCompanion Context triple: [Saint Jovita, hasSiblingOrCompanion, Saint Faustinus]
-
A.
hasSiblingTrio
Indicates that an entity is part of a group of exactly three siblings who are related to each other.
-
B.
hasSisterRelationshipType
Indicates that there exists a sister-type familial relationship between the related entities.
-
C.
hasCompanionCandidate
Indicates that an entity is associated with another entity that is being considered or proposed as a potential companion.
-
D.
hasSiblingMembers
chosen
Indicates that two entities are members of a group or organization and are siblings to each other within that membership context.
-
E.
hasSiblingStars
Indicates that two or more stars share at least one common parent system or origin, making them siblings in an astrophysical or formation context.
- 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_69f09123ed9881909f351f7541933f5e |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69f7688dd3d08190ad13d0e780570a1c |
completed | May 3, 2026, 3:23 p.m. |
| PD | Predicate disambiguation | batch_69f767fcf2f881908bacc7bfc38e68a5 |
completed | May 3, 2026, 3:21 p.m. |
Created at: April 28, 2026, 1:14 p.m.