Triple
T10983152
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | James Leo Herlihy |
E259558
|
entity |
| Predicate | wrote |
P2831
|
FINISHED |
| Object | Crazy Joe |
E489491
|
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: Crazy Joe | Statement: [James Leo Herlihy, wrote, Crazy Joe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Crazy Joe Context triple: [James Leo Herlihy, wrote, Crazy Joe]
-
A.
Lepke
Lepke was the underworld nickname of Louis Buchalter, a notorious American mobster and leader of the contract killing organization Murder, Inc.
-
B.
Tito Burns
Tito Burns was a British accordionist-turned-music manager and agent who became a prominent figure in the UK entertainment industry from the 1950s onward.
-
C.
Crazy Joe Gallo
chosen
Crazy Joe Gallo was a notorious New York City mobster and hitman associated with the Colombo crime family during the mid-20th century.
-
D.
Gotti
"Gotti" is a 2018 single by American rapper Tekashi 6ix9ine, known for its melodic style and inclusion on the expanded version of his debut mixtape, *Day69*.
-
E.
Gotti
Gotti is a 1996 television crime drama film in which Armand Assante portrays notorious mob boss John Gotti.
- 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_69d6aa895f4c8190887a15460ef622f4 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d772ec55fc81909b2b15f2493dddc6 |
completed | April 9, 2026, 9:35 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e344c77d6c8190a9b5e2cc967fb031 |
completed | April 18, 2026, 8:45 a.m. |
Created at: April 8, 2026, 9:24 p.m.