Triple
T32849159
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ludovico Ludovisi |
E840194
|
entity |
| Predicate | servedInCuriaUnder |
P199559
|
FINISHED |
| Object | Pope Gregory XV |
—
|
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: Pope Gregory XV | Statement: [Ludovico Ludovisi, servedInCuriaUnder, Pope Gregory XV]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servedInCuriaUnder Context triple: [Ludovico Ludovisi, servedInCuriaUnder, Pope Gregory XV]
-
A.
hasCuria
Indicates that an entity possesses, is associated with, or is served by a specific curia (council, court, or governing body).
-
B.
hadJudicialFunction
Indicates that an entity exercised or was assigned an official judicial role, authority, or responsibility in relation to another entity or context.
-
C.
clerkedFor
Indicates that one person served as a judicial clerk or legal assistant to another, typically a judge or justice.
-
D.
servedOnSupremeCourtUntil
Indicates that an individual held a position on the Supreme Court up to and including a specified end date.
-
E.
servedAtCourtOf
Indicates that an individual performed official duties or held a position in the court of a particular ruler or governing authority.
- 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_69f349412c78819084459850e11d29f7 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69ff45793d5c81909dc503ad1f714ee2 |
completed | May 9, 2026, 2:32 p.m. |
| PD | Predicate disambiguation | batch_69ff41cb0e088190a6e9b03cb20e5fad |
completed | May 9, 2026, 2:16 p.m. |
| PDg | Predicate description generation | batch_69ff45782cb88190b604811e4d724382 |
completed | May 9, 2026, 2:32 p.m. |
Created at: May 1, 2026, 1:17 a.m.