Triple
T20780748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mariko Yashida |
E511472
|
entity |
| Predicate | romanticPartner |
P9994
|
FINISHED |
| Object | Logan |
—
|
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: Logan | Statement: [Mariko Yashida, romanticPartner, Logan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Logan Context triple: [Mariko Yashida, romanticPartner, Logan]
-
A.
Logan
Logan is a name commonly used as both a given name and surname in English-speaking countries.
-
B.
Logan
Logan is a small village in eastern New Mexico, United States, known for its proximity to Ute Lake and its role as a local recreational and service hub in Quay County.
-
C.
Logan
Logan is a small village located within the council area of East Ayrshire in southwest Scotland.
-
D.
Logan
Logan is a residential neighborhood in North Philadelphia, Pennsylvania, known for its rowhouses and proximity to institutions like La Salle University.
-
E.
Logan
chosen
Logan is a Marvel Comics antihero better known as Wolverine, a mutant with retractable claws and a powerful healing factor who was subjected to the Weapon X program.
- 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_69e0b4cac7a48190a715cb3d545df2b4 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c26f99b88190a84a6889834e1e96 |
completed | April 21, 2026, 12:18 a.m. |
Created at: April 16, 2026, 12:37 p.m.