Triple
T35146505
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clyth |
E1014851
|
entity |
| Predicate | ancestralHeartlandOf |
P38603
|
FINISHED |
| Object | Clan Gunn |
—
|
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: Clan Gunn | Statement: [Clyth, ancestralHeartlandOf, Clan Gunn]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ancestralHeartlandOf Context triple: [Clyth, ancestralHeartlandOf, Clan Gunn]
-
A.
secondaryAncestralHomeland
Indicates a place that serves as an additional or subsequent ancestral homeland for a group or lineage, distinct from their primary place of origin.
-
B.
ancestralCounty
Indicates that one entity is the county from which another entity or its ancestors originate.
-
C.
originOfSettlement
Indicates the place, source, or starting point from which a settlement was established or originated.
-
D.
landsPreviouslyBelongedTo
Indicates that the specified lands were owned, controlled, or possessed by a different party at an earlier time.
-
E.
originalHomeland
chosen
Indicates the place or region that is considered the ancestral or earliest homeland of an entity.
- 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_69f76dda7c108190a2ffd93eb6c341a7 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f78caef6448190895972bdebbbc62e |
completed | May 3, 2026, 5:58 p.m. |
| PD | Predicate disambiguation | batch_69f78b9106008190930b3b3675b737d6 |
completed | May 3, 2026, 5:53 p.m. |
Created at: May 3, 2026, 4:02 p.m.