Triple
T6991169
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lycaon pictus |
E162088
|
entity |
| Predicate | packHierarchy |
P41995
|
FINISHED |
| Object | dominant breeding pair |
—
|
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: dominant breeding pair | Statement: [Lycaon pictus, packHierarchy, dominant breeding pair]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: packHierarchy Context triple: [Lycaon pictus, packHierarchy, dominant breeding pair]
-
A.
orderHierarchy
Indicates a hierarchical ordering relationship where one entity is positioned above or below another in a structured sequence or chain of command.
-
B.
hasHierarchyIn
chosen
Indicates that one entity occupies a higher or lower level within an ordered structure or chain of command relative to another entity in a specified context.
-
C.
lapStructure
Indicates that one entity forms a lap-like structural surface or support upon which another entity can rest or be positioned.
-
D.
titleHierarchy
Indicates a hierarchical relationship between titles, where one title is ranked above or below another in an ordered structure.
-
E.
categoryStructure
Indicates the hierarchical or organizational relationship that defines how categories are structured and arranged relative to one another.
- 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_69c68856d7808190ab33ee914640281b |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6dbc08758819083d36a1fc0463b27 |
completed | March 27, 2026, 7:34 p.m. |
| PD | Predicate disambiguation | batch_69c6d7c4a18881908d267137daed828b |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:32 p.m.