Triple
T12469022
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Welsh 3000s |
E298003
|
entity |
| Predicate | includesPeak |
P53629
|
FINISHED |
| Object | Foel Grach |
E853174
|
NE 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: Foel Grach | Statement: [Welsh 3000s, includesPeak, Foel Grach]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Foel Grach Context triple: [Welsh 3000s, includesPeak, Foel Grach]
-
A.
Foel Grach
chosen
Foel Grach is a prominent mountain in the Carneddau range of Snowdonia, Wales, known for its high, rounded summit and remote, rugged setting.
-
B.
Arawn
Arawn is a ruler of the Otherworld in Welsh mythology, often associated with the realm of Annwn and the themes of death, the hunt, and the supernatural.
-
C.
Ancalagon the Black
Ancalagon the Black is a colossal and most powerful dragon of Morgoth in J.R.R. Tolkien’s legendarium, whose defeat marked the decisive turning point in the War of Wrath.
-
D.
Svarog
Svarog is the Slavic god of the sky, fire, and blacksmithing, often regarded as a creator deity and divine craftsman.
-
E.
Mor'du
Mor'du is the monstrous, cursed bear and primary antagonist in Disney-Pixar's animated film "Brave."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6ada270808190b1a2b2e7b02bb426 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94db979c481908778188794b2c08e |
completed | April 10, 2026, 7:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f63f2175c48190bbd28ad8c07434f0 |
completed | May 2, 2026, 6:14 p.m. |
Created at: April 8, 2026, 9:56 p.m.