Triple
T23919879
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sadr al-Din Muhammad ibn Ibrahim |
E602186
|
entity |
| Predicate | mainInterests |
P44657
|
FINISHED |
| Object | metaphysics |
—
|
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: metaphysics | Statement: [Sadr al-Din Muhammad ibn Ibrahim, mainInterests, metaphysics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainInterests Context triple: [Sadr al-Din Muhammad ibn Ibrahim, mainInterests, metaphysics]
-
A.
primaryInterest
chosen
Indicates that one entity is the main or most significant focus of attention, concern, or engagement for another entity.
-
B.
subjectInterest
Indicates that the subject has an interest in, or is concerned with, the object.
-
C.
secondaryInterest
Indicates that an entity has a secondary, less primary but still relevant interest or focus in relation to another entity or topic.
-
D.
activityCorrelatesWith
Indicates that the level or occurrence of one activity is statistically associated with the level or occurrence of another activity, without implying direct causation.
-
E.
hasOverlappingInterestsFrom
Indicates that one entity shares some, but not necessarily all, interests in common with another entity, such that their sets of interests partially overlap.
- 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_69e2953a187081908346a9f36e85fc98 |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1cf1772e08190a434c91f4e7437b4 |
completed | April 29, 2026, 9:27 a.m. |
| PD | Predicate disambiguation | batch_69f16151ebdc819086e9e1d7cc1f4f3c |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:41 p.m.