Triple
T20525480
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wesley Gibson |
E503922
|
entity |
| Predicate | hasEnemy |
P4675
|
FINISHED |
| Object | Cross |
—
|
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: Cross | Statement: [Wesley Gibson, hasEnemy, Cross]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cross Context triple: [Wesley Gibson, hasEnemy, Cross]
-
A.
Cross
chosen
Cross is a common English surname borne by numerous notable individuals in fields such as entertainment, sports, and politics.
-
B.
Cross
Cross is an experimental artwork by American assemblage and collage artist Wallace Berman, reflecting his pioneering role in the Beat-era avant-garde.
-
C.
Right Cross
Right Cross is a 1950 American sports drama film centered on professional boxing, directed by John Sturges and starring June Allyson and Ricardo Montalbán.
-
D.
Cros
Cros is a French surname most notably associated with Charles Cros, a 19th-century poet and inventor linked to early sound recording and color photography experiments.
-
E.
Cross Counter
Cross Counter is a British Thoroughbred racehorse best known for winning the 2018 Melbourne Cup.
- 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_69e0b4b3a6e08190ae663701f50fab8e |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a06504b48190b3f1defdc23a47d5 |
completed | April 20, 2026, 9:53 p.m. |
Created at: April 16, 2026, 11:37 a.m.