Triple
T2368141
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Philippians 2:10–11 |
E46029
|
entity |
| Predicate | addressesScope |
P13939
|
FINISHED |
| Object | in heaven |
—
|
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: in heaven | Statement: [Philippians 2:10–11, addressesScope, in heaven]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: addressesScope Context triple: [Philippians 2:10–11, addressesScope, in heaven]
-
A.
locationScope
chosen
Indicates the specific geographic or spatial area within which a given relationship, condition, or action is considered valid or applicable.
-
B.
addressesRole
Indicates that one entity directs communication, content, or action specifically toward another entity in its capacity or function as a particular role.
-
C.
scopeOfRecipients
Indicates the range or group of recipients to whom something (such as information, communication, or benefits) is directed or applicable.
-
D.
organizationalScope
Indicates the range or extent of responsibility, authority, or applicability that an action, policy, or relationship has within an organization or its sub-units.
-
E.
identificationScope
Indicates the contextual boundary or extent within which an entity is uniquely identified or recognized.
- 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_69a88a145268819083e2736cb835c696 |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abc76bf75c8190b014c3dbfc46bba3 |
completed | March 7, 2026, 6:36 a.m. |
| PD | Predicate disambiguation | batch_69abc59b88348190a2d6c08f69974117 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:56 p.m.