Triple
T35619399
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sissanese |
E1029268
|
entity |
| Predicate | traditionalLocality |
P49478
|
FINISHED |
| Object | Sissano |
—
|
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: Sissano | Statement: [Sissanese, traditionalLocality, Sissano]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traditionalLocality Context triple: [Sissanese, traditionalLocality, Sissano]
-
A.
modernLocality
Indicates that an entity is located in, associated with, or corresponds to a present-day geographic or administrative locality.
-
B.
localityOf
Indicates that one entity is the specific place, area, or locality in which another entity is situated or occurs.
-
C.
traditionalDistrict
chosen
Indicates that an entity is located in, associated with, or belongs to a historically recognized or customary administrative or cultural district.
-
D.
originLocality
Indicates the specific locality or place where an entity (typically a specimen or item) originally came from or was collected.
-
E.
traditionalInCity
Indicates that something is customary, long-established, or historically rooted within a particular city.
- 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_69f76e0709408190bbe322bf1707ef6b |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69ff6fba1a5c8190a660279a6271d785 |
completed | May 9, 2026, 5:32 p.m. |
| PD | Predicate disambiguation | batch_69ff6f59388c8190a7d6ab7bc7705bc0 |
completed | May 9, 2026, 5:31 p.m. |
Created at: May 3, 2026, 4:05 p.m.