Triple
T19882030
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nestor (Ulysses episode) |
E477797
|
entity |
| Predicate | basedOn |
P98
|
FINISHED |
| Object | Homeric figure Nestor |
—
|
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: Homeric figure Nestor | Statement: [Nestor (Ulysses episode), basedOn, Homeric figure Nestor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Homeric figure Nestor Context triple: [Nestor (Ulysses episode), basedOn, Homeric figure Nestor]
-
A.
Nestor, king of Pylos
chosen
Nestor, king of Pylos, is a wise and elderly Greek hero in Homeric epic, renowned for his eloquent counsel and experience in war.
-
B.
Nestor
Nestor is the loyal and unflappable butler of Marlinspike Hall in Hergé’s "The Adventures of Tintin" series.
-
C.
Nestor
Nestor is a genus of large, intelligent New Zealand parrots that includes species such as the kea and the kaka.
-
D.
Nestor
Nestor is a residential neighborhood in the southern part of San Diego, California, located near the U.S.–Mexico border.
-
E.
Nestor
Nestor is the wise and elderly king of Pylos in Greek mythology, renowned for his counsel to heroes in Homer's epics.
- 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_69d8e51f32b08190b3687f4f60353250 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e658df3f5c81909b5b290de91b8d50 |
completed | April 20, 2026, 4:48 p.m. |
Created at: April 10, 2026, 1:52 p.m.