Triple
T19355831
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | E. H. Harriman |
E484141
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object |
Henry
Henry is the first name of American railroad executive and financier E. H. Harriman.
|
E1374309
|
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: Henry | Statement: [E. H. Harriman, givenName, Henry]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Henry Context triple: [E. H. Harriman, givenName, Henry]
-
A.
Henry
Henry is a comedic, aging actor character in the long-running musical "The Fantasticks," known for his over-the-top theatricality and forgetfulness.
-
B.
John
John is a masculine given name of Hebrew origin, widely used in English-speaking countries and borne by numerous historical and contemporary figures.
-
C.
John
John is the nickname of John Riggins, a former American football running back best known for his Hall of Fame career with the Washington Redskins in the NFL.
-
D.
John
John is the given name of John Adams, the prominent American minimalist and post-minimalist composer known for works like "Nixon in China" and "Short Ride in a Fast Machine."
-
E.
John
John is the given name of actor John Cho, a Korean American performer known for roles in the "Harold & Kumar" films and the "Star Trek" reboot series.
- 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: Henry Triple: [E. H. Harriman, givenName, Henry]
Generated description
Henry is the first name of American railroad executive and financier E. H. Harriman.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Henry Target entity description: Henry is the first name of American railroad executive and financier E. H. Harriman.
-
A.
Henry
Henry is the given name of Henry B. Plant, the prominent 19th-century American railroad and hotel magnate who developed much of Florida’s transportation infrastructure.
-
B.
Henry
Henry is the given name of the influential American architect Henry Hobson Richardson, a key figure in 19th-century architecture.
-
C.
Henry
Henry is the given first name of American businessman and politician Ross Perot, who was a prominent third-party U.S. presidential candidate in the 1990s.
-
D.
Henry
Henry is the given first name of Hank Steinbrenner, a late co-owner and general partner of the New York Yankees baseball team.
-
E.
Henry
Henry is the given name of Henry A. Kissinger, the influential American diplomat and political scientist who served as U.S. Secretary of State and National Security Advisor.
- 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_69d8e8d305088190ad13571532aa454c |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e61908920c8190833051e30ad2420c |
completed | April 20, 2026, 12:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a072b75a2108190bce47e8156734593 |
completed | May 15, 2026, 2:19 p.m. |
| NEDg | Description generation | batch_6a072e9f4f688190a83dc4943a690f76 |
completed | May 15, 2026, 2:33 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a072f8b7248819093533bbc0802721f |
completed | May 15, 2026, 2:36 p.m. |
Created at: April 10, 2026, 1:34 p.m.