Triple
T22990257
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crato (urban area) |
E572026
|
entity |
| Predicate | hasName |
P744
|
FINISHED |
| Object | Crato |
—
|
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: Crato | Statement: [Crato (urban area), hasName, Crato]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Crato Context triple: [Crato (urban area), hasName, Crato]
-
A.
Crato
Crato is a historic city in northeastern Brazil known for its cultural heritage and proximity to the Araripe Plateau in the state of Ceará.
-
B.
Crato
chosen
Crato is a town and municipality in the Portalegre District of the Alentejo region in Portugal, known for its historical significance and religious heritage.
-
C.
Andautonia
Andautonia was an important ancient Roman settlement and administrative center in the province of Pannonia, located near present-day Zagreb in Croatia.
-
D.
Niceratus
Niceratus is a character in Xenophon’s works, depicted as the wealthy and educated son of the Athenian general Nicias.
-
E.
Charondas
Charondas was an ancient Greek lawgiver, traditionally credited with establishing a notable legal code for several Greek colonies in southern Italy and Sicily.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245b535808190adef8a9df3c584db |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f182ee3afc819099fbc6bef0b83bd5 |
completed | April 29, 2026, 4:02 a.m. |
Created at: April 17, 2026, 3:49 p.m.