Triple
T11599254
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Herbert J. Krapp |
E275083
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object |
Herts & Tallant
Herts & Tallant was a prominent early 20th-century American architectural firm known for designing numerous Broadway and New York City theaters.
|
E936104
|
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: Herts & Tallant | Statement: [Herbert J. Krapp, employer, Herts & Tallant]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Herts & Tallant Context triple: [Herbert J. Krapp, employer, Herts & Tallant]
-
A.
Tallant
Tallant is a character in the play "The Late Christopher Bean," typically portrayed as an art expert whose arrival helps reveal the true value and significance of the late painter’s work.
-
B.
The Hartlepools
The Hartlepools was a UK parliamentary constituency in County Durham that historically elected Members of Parliament to the House of Commons.
-
C.
Up Hatherley
Up Hatherley is a suburban residential area and civil parish on the outskirts of Cheltenham in Gloucestershire, England.
-
D.
Happy Hinds
Happy Hinds is the child of American R&B and soul singer-songwriter Macy Gray.
-
E.
Hackett
Hackett is a surname of English and Irish origin borne by various notable individuals across fields such as literature, sports, and entertainment.
- 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: Herts & Tallant Triple: [Herbert J. Krapp, employer, Herts & Tallant]
Generated description
Herts & Tallant was a prominent early 20th-century American architectural firm known for designing numerous Broadway and New York City theaters.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Herts & Tallant Target entity description: Herts & Tallant was a prominent early 20th-century American architectural firm known for designing numerous Broadway and New York City theaters.
-
A.
Tallant
Tallant is a character in the play "The Late Christopher Bean," typically portrayed as an art expert whose arrival helps reveal the true value and significance of the late painter’s work.
-
B.
The Hartlepools
The Hartlepools was a UK parliamentary constituency in County Durham that historically elected Members of Parliament to the House of Commons.
-
C.
Up Hatherley
Up Hatherley is a suburban residential area and civil parish on the outskirts of Cheltenham in Gloucestershire, England.
-
D.
Happy Hinds
Happy Hinds is the child of American R&B and soul singer-songwriter Macy Gray.
-
E.
Hackett
Hackett is a surname of English and Irish origin borne by various notable individuals across fields such as literature, sports, and entertainment.
- 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_69d6aae6b14c81908dc5a74bad7591f9 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8954c3c248190bcccd4c7ff667b3a |
completed | April 10, 2026, 6:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e8a7dd83d48190b281a6fcfc3e4087 |
completed | April 22, 2026, 10:50 a.m. |
| NEDg | Description generation | batch_69e8af93e07c8190aecb040cac6db146 |
completed | April 22, 2026, 11:23 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ee5b254a2081909cba97a6ecb10601 |
completed | April 26, 2026, 6:36 p.m. |
Created at: April 8, 2026, 9:38 p.m.