Triple
T35242
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Virgin Mary |
E698
|
entity |
| Predicate | childOf |
P120
|
FINISHED |
| Object | Saint Joachim |
E4646
|
NE 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: Saint Joachim | Statement: [Virgin Mary, childOf, Saint Joachim]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saint Joachim Context triple: [Virgin Mary, childOf, Saint Joachim]
-
A.
Saint Joseph
Saint Joseph is a key figure in Christianity, venerated as the earthly father of Jesus and a model of humility, obedience, and protective care.
-
B.
Deacon Phillippe
Deacon Phillippe was a prominent early 20th-century Major League Baseball pitcher, best known for his standout performances with the Pittsburgh Pirates, including in the inaugural 1903 World Series.
-
C.
Johan
Johan is the given first name of J. Erik Jonsson, an American businessman and philanthropist who co-founded Texas Instruments and served as mayor of Dallas.
-
D.
Saint Anne
chosen
Saint Anne is traditionally venerated in Christian theology as the mother of the Virgin Mary and the grandmother of Jesus.
-
E.
Joseph
Joseph is the first name of J. C. R. Licklider, a pioneering computer scientist often regarded as a key figure in the development of the internet and interactive computing.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a2479dec388190967ba648663442c9 |
completed | Feb. 28, 2026, 1:40 a.m. |
| NER | Named-entity recognition | batch_69a24aca5ed481908d1aa2ca656f25ea |
completed | Feb. 28, 2026, 1:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a25ab3438c81908ff16eb23a09fea7 |
completed | Feb. 28, 2026, 3:02 a.m. |
Created at: Feb. 28, 2026, 1:44 a.m.