Triple
T22551178
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mên-an-Tol |
E557559
|
entity |
| Predicate | hasAlternativeName |
P39
|
FINISHED |
| Object | Men-an-Tol |
—
|
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: Men-an-Tol | Statement: [Mên-an-Tol, hasAlternativeName, Men-an-Tol]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Men-an-Tol Context triple: [Mên-an-Tol, hasAlternativeName, Men-an-Tol]
-
A.
Mên-an-Tol
chosen
Mên-an-Tol is a distinctive Bronze Age megalithic monument in Cornwall, England, best known for its iconic holed stone flanked by two upright stones and associated with local healing and fertility folklore.
-
B.
Menendo
Menendo is a medieval Iberian given name of likely Germanic origin that served as the root for the patronymic surname Menéndez.
-
C.
De Meent
De Meent is a central shopping center in the Dutch town of Papendrecht, offering a variety of retail stores and services.
-
D.
Tollin
Tollin is a surname most notably associated with American film and television producer and director Mike Tollin.
-
E.
Menmaatre
Menmaatre was the throne name of the ancient Egyptian pharaoh Seti I of the Nineteenth Dynasty.
- 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_69e11e59db848190b4272ecd2b690ffd |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15f7546c4819099942c86ca522a60 |
completed | April 29, 2026, 1:31 a.m. |
Created at: April 16, 2026, 8:52 p.m.