Triple
T4977743
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Sheeran |
E111809
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object |
Francis
Francis is the given name of Frank Sheeran, the American labor union official and alleged mob hitman whose life inspired the film "The Irishman."
|
E485610
|
NE FINISHED |
How this triple was built (4 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: Francis | Statement: [Frank Sheeran, givenName, Francis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Francis Context triple: [Frank Sheeran, givenName, Francis]
-
A.
Francis
Francis is the given first name of legendary Los Angeles Lakers play-by-play announcer Chick Hearn.
-
B.
Francis
Francis is the middle name of American seismologist Charles Francis Richter, best known for creating the Richter magnitude scale for measuring earthquakes.
-
C.
Francis
Francis is the given first name of Canadian ice hockey player and Hall of Famer King Clancy.
-
D.
Francis
Francis was a German nobleman who served as Duke of Saxe-Coburg-Saalfeld in the late 18th and early 19th centuries.
-
E.
Francis
Francis is the papal name of the current head of the Roman Catholic Church, known for his emphasis on humility, social justice, and interfaith dialogue.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Francis Triple: [Frank Sheeran, givenName, Francis]
Generated description
Francis is the given name of Frank Sheeran, the American labor union official and alleged mob hitman whose life inspired the film "The Irishman."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Francis Target entity description: Francis is the given name of Frank Sheeran, the American labor union official and alleged mob hitman whose life inspired the film "The Irishman."
-
A.
Francis
Francis is the given first name of the American author and poet Bret Harte, known for his stories of the California Gold Rush.
-
B.
Francis
Francis is the formal given name of Frank Nighbor, a famed early 20th-century Canadian ice hockey player and Hall of Famer.
-
C.
Francis
Francis is the given first name of Canadian ice hockey player and Hall of Famer King Clancy.
-
D.
Francis
Francis is a masculine given name of Latin origin, commonly used in English-speaking countries and associated with figures such as Saint Francis of Assisi and numerous historical and contemporary personalities.
-
E.
Francis
Francis is the middle name of Samuel Francis Du Pont, a prominent 19th-century U.S. Navy admiral from the Du Pont family.
- F. None of above. chosen
Provenance (5 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_69bd441adc208190b70a033a0741d01e |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd7232bd8c8190b325c9198e8b2fa1 |
completed | March 20, 2026, 4:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be8a0634b48190acb4a1834f5647cf |
completed | March 21, 2026, 12:07 p.m. |
| NEDg | Description generation | batch_69be8a9c72848190978797a33d0d83c8 |
completed | March 21, 2026, 12:10 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69be8b3718288190b2fc319fdad0a7c0 |
completed | March 21, 2026, 12:12 p.m. |
Created at: March 20, 2026, 1:33 p.m.