Triple
T27384581
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abu Ahmad ibn Jahsh |
E691331
|
entity |
| Predicate | relativeThroughMarriageOf |
P167266
|
FINISHED |
| Object | Muhammad |
—
|
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: Muhammad | Statement: [Abu Ahmad ibn Jahsh, relativeThroughMarriageOf, Muhammad]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relativeThroughMarriageOf Context triple: [Abu Ahmad ibn Jahsh, relativeThroughMarriageOf, Muhammad]
-
A.
characterRelativeByMarriage
chosen
Indicates that one character is related to another through marriage rather than by blood.
-
B.
connectedThroughMarriageVia
Indicates that two entities are related to each other by a marital connection that is mediated through one or more intermediate spouses or in-laws, rather than by a direct marriage between them.
-
C.
marriedToFrom
Indicates that one entity is married to another, with the direction emphasizing the spouse or origin of the marital relationship.
-
D.
marriedBy
Indicates that one entity is the officiant or authority who performs and formalizes the marriage of another entity.
-
E.
marriageLinkedBranch
Indicates a connection between two branches or lineages that is established or traced through a marriage relationship.
- 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_69ef520386788190bc92cfcd97ebb67a |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69ff63225b6481909217ad11b4f7d3ba |
completed | May 9, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_69ff60e0882c819085d097010db43ee0 |
completed | May 9, 2026, 4:29 p.m. |
Created at: April 27, 2026, 12:24 p.m.