Triple
T38590658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hyur |
E932444
|
entity |
| Predicate | hasNotableClanTrait |
P115426
|
FINISHED |
| Object | Midlanders are of average build |
—
|
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: Midlanders are of average build | Statement: [Hyur, hasNotableClanTrait, Midlanders are of average build]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNotableClanTrait Context triple: [Hyur, hasNotableClanTrait, Midlanders are of average build]
-
A.
hasSubclan
Indicates that one clan contains or is composed of a smaller, subordinate clan within its structure.
-
B.
hasFamilyTrait
chosen
Indicates that a particular trait or characteristic is shared among members of the same family or lineage.
-
C.
clanType
Indicates the specific category or classification of a clan within a broader clan system or hierarchy.
-
D.
hasNotableTraitInPlot
Indicates that a character or entity possesses a distinctive trait that plays a significant role within the narrative or plot.
-
E.
notableClans
Indicates that there exists a significant or historically important clan associated with the subject.
- 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_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a2026248190b894436a578d79ac |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:32 p.m.