Triple
T21479971
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | warship Michael |
E529961
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object | Great Michael |
—
|
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: Great Michael | Statement: [warship Michael, alsoKnownAs, Great Michael]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Great Michael Context triple: [warship Michael, alsoKnownAs, Great Michael]
-
A.
Great Michael
chosen
Great Michael was a massive early 16th-century Scottish warship, famed as one of the largest and most heavily armed vessels of its time.
-
B.
Crystal Tower
Crystal Tower is a prominent high-rise office skyscraper in Osaka, Japan, known for its sleek glass façade and location within the Osaka Business Park.
-
C.
Crystal Tower
Crystal Tower is an ancient, legendary Altmer structure on Summerset Isle in The Elder Scrolls universe, renowned for its immense magical power and central role in elven history and lore.
-
D.
Crystal Tower
Crystal Tower is a prominent skyscraper in Madrid, Spain, known as one of the city’s tallest and most modern office buildings.
-
E.
Martin Tower
Martin Tower is one of the prominent towers of Basel Minster, a historic Gothic cathedral in Basel, Switzerland.
- 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_69e0c45acc3881908e38d3f28964152b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea1b0130819088b8e96ddbb29317 |
completed | April 23, 2026, 9:44 a.m. |
Created at: April 16, 2026, 6:20 p.m.