Triple
T34481536
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ka‘b ibn Lu’ayy |
E885199
|
entity |
| Predicate | lineagePosition |
P179404
|
FINISHED |
| Object | ancestor several generations before Prophet Muhammad |
—
|
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: ancestor several generations before Prophet Muhammad | Statement: [Ka‘b ibn Lu’ayy, lineagePosition, ancestor several generations before Prophet Muhammad]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lineagePosition Context triple: [Ka‘b ibn Lu’ayy, lineagePosition, ancestor several generations before Prophet Muhammad]
-
A.
lineageSystem
Indicates a hierarchical ancestry or descent relationship that traces how entities are derived from or originate through one another within a system.
-
B.
positionOnLine
Indicates that one entity occupies a specific location along a defined line or linear path in relation to another.
-
C.
leafPosition
Indicates the spatial or structural placement of a leaf relative to its supporting plant organ or axis.
-
D.
linePositioning
Indicates how one line is spatially arranged or oriented in relation to another line.
-
E.
linePositioning
Indicates the relative arrangement or alignment of elements along a line or linear sequence.
- F. None of above. chosen
Provenance (4 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_69f349c947fc81909d30b53c194d6ea1 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f720cc1bfc8190a16118e3af8e9316 |
completed | May 3, 2026, 10:17 a.m. |
| PD | Predicate disambiguation | batch_69f71cc6397881909aaad37a9daa8a7e |
completed | May 3, 2026, 10 a.m. |
| PDg | Predicate description generation | batch_69f71fb0172c81908f23e95ff16b0dec |
completed | May 3, 2026, 10:13 a.m. |
Created at: May 1, 2026, 2:01 a.m.