Triple
T9950658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marsh v. Chambers |
E195319
|
entity |
| Predicate | chaplainType |
P3092
|
FINISHED |
| Object | state-funded legislative chaplain |
—
|
LITERAL 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: state-funded legislative chaplain | Statement: [Marsh v. Chambers, chaplainType, state-funded legislative chaplain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chaplainType Context triple: [Marsh v. Chambers, chaplainType, state-funded legislative chaplain]
-
A.
hasChaplain
Indicates that an entity is served or attended to by a designated chaplain.
-
B.
clergySystem
Indicates a relationship in which an organized religious institution or tradition has a structured system of clergy roles, ranks, or offices.
-
C.
hasClergyType
chosen
Indicates the specific category or role of clergy associated with an entity.
-
D.
clergyCan
Indicates that members of the clergy are permitted or authorized to perform a specified action or exercise a particular role or function.
-
E.
clergy
Indicates that an entity serves in an official religious or spiritual leadership role within an organized faith or religious institution.
- 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_69ca82e96a108190932bd1fc4acd73a0 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb65b83ac8190af6bd8c918ffb69f |
completed | April 2, 2026, 12:20 a.m. |
| PD | Predicate disambiguation | batch_69cd1d97c44081908730071269f07712 |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:45 p.m.