Triple
T25215230
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clara Bowden |
E631809
|
entity |
| Predicate | hasReligiousUpbringing |
P136960
|
FINISHED |
| Object | Jehovah’s Witness |
—
|
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: Jehovah’s Witness | Statement: [Clara Bowden, hasReligiousUpbringing, Jehovah’s Witness]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasReligiousUpbringing Context triple: [Clara Bowden, hasReligiousUpbringing, Jehovah’s Witness]
-
A.
hasReligiousParent
Indicates that an entity has a parent who is associated with or practices a particular religion.
-
B.
hasReligious
chosen
Indicates that an entity is associated with, practices, or adheres to a particular religion or religious affiliation.
-
C.
religiousUpbringingPlaceOf
Indicates the place or location where an individual received their religious upbringing.
-
D.
raisedChildInReligion
Indicates that one entity brought up or nurtured another entity within a particular religious tradition or faith.
-
E.
hasReligiousOrigin
Indicates that something originates from, is derived from, or is fundamentally based on a religious tradition, belief system, or practice.
- 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_69e75a8d1aa48190a4320acd3654762c |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f7221dc9a88190bb8194fcc29c42bc |
completed | May 3, 2026, 10:23 a.m. |
| PD | Predicate disambiguation | batch_69f72153a9188190b02adc84e1be4af8 |
completed | May 3, 2026, 10:20 a.m. |
Created at: April 21, 2026, 12:58 p.m.