Triple
T16674340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mummer |
E405179
|
entity |
| Predicate | recordedAt |
P7677
|
FINISHED |
| Object |
The Town House
The Town House is a professional recording studio known for hosting music sessions such as those by the band Mummer.
|
E1227362
|
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: The Town House | Statement: [Mummer, recordedAt, The Town House]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Town House Context triple: [Mummer, recordedAt, The Town House]
-
A.
Shell House
Shell House was the former Johannesburg headquarters of South Africa’s African National Congress, later renamed Luthuli House.
-
B.
World-Wide House
World-Wide House is a prominent commercial office and retail building in Central, Hong Kong, known for its bustling arcade of small shops and services.
-
C.
City House
City House is a commercial office building located in Croydon town centre in South London.
-
D.
Lee House
Lee House is one of the historic townhouses that together form the Blair House complex, the official guest residence for visiting dignitaries in Washington, D.C.
-
E.
Udbodhan House
Udbodhan House is a historic building in Kolkata that served as the residence of Sarada Devi and the headquarters of the Bengali magazine "Udbodhan," closely linked with the early Ramakrishna Movement.
- 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: The Town House Triple: [Mummer, recordedAt, The Town House]
Generated description
The Town House is a professional recording studio known for hosting music sessions such as those by the band Mummer.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: The Town House Target entity description: The Town House is a professional recording studio known for hosting music sessions such as those by the band Mummer.
-
A.
Shell House
Shell House was the former Johannesburg headquarters of South Africa’s African National Congress, later renamed Luthuli House.
-
B.
World-Wide House
World-Wide House is a prominent commercial office and retail building in Central, Hong Kong, known for its bustling arcade of small shops and services.
-
C.
City House
City House is a commercial office building located in Croydon town centre in South London.
-
D.
Lee House
Lee House is one of the historic townhouses that together form the Blair House complex, the official guest residence for visiting dignitaries in Washington, D.C.
-
E.
Udbodhan House
Udbodhan House is a historic building in Kolkata that served as the residence of Sarada Devi and the headquarters of the Bengali magazine "Udbodhan," closely linked with the early Ramakrishna Movement.
- 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_69d8838c28748190b3f5967c743940ab |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37d6904008190a79ab30b6d9ccae9 |
completed | April 18, 2026, 12:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a008a3ab8b481908b333b6a556a58d5 |
completed | May 10, 2026, 1:38 p.m. |
| NEDg | Description generation | batch_6a008ad087b08190b725382c68687a15 |
completed | May 10, 2026, 1:40 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a008ba8227881908b1ac6e30d2e7c32 |
completed | May 10, 2026, 1:44 p.m. |
Created at: April 10, 2026, 5:19 a.m.