Triple
T22591778
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bebo |
E564967
|
entity |
| Predicate | founder |
P104
|
FINISHED |
| Object |
Michael Birch
Michael Birch is a British entrepreneur best known for co-founding the social networking site Bebo and later selling it for hundreds of millions of dollars.
|
E1545205
|
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: Michael Birch | Statement: [Bebo, founder, Michael Birch]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Birch Context triple: [Bebo, founder, Michael Birch]
-
A.
Michael Korie
Michael Korie is an American lyricist and librettist known for his work in musical theatre and opera, including collaborations on acclaimed shows such as Grey Gardens.
-
B.
Mike Lange
Mike Lange is a renowned American sportscaster best known as the longtime, colorful play-by-play announcer for the NHL’s Pittsburgh Penguins.
-
C.
Mike Lange
Mike Lange is a musician best known as a member of the Celtic rock band O'Malley's March.
-
D.
Cam Gigandet
Cam Gigandet is an American actor known for his roles in films such as "Twilight," "Never Back Down," and various television series.
-
E.
David Hackney
David Hackney was an American guitarist and songwriter best known as a founding member of the pioneering Detroit proto-punk band Death.
- 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: Michael Birch Triple: [Bebo, founder, Michael Birch]
Generated description
Michael Birch is a British entrepreneur best known for co-founding the social networking site Bebo and later selling it for hundreds of millions of dollars.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Michael Birch Target entity description: Michael Birch is a British entrepreneur best known for co-founding the social networking site Bebo and later selling it for hundreds of millions of dollars.
-
A.
Michael Korie
Michael Korie is an American lyricist and librettist known for his work in musical theatre and opera, including collaborations on acclaimed shows such as Grey Gardens.
-
B.
Mike Lange
Mike Lange is a musician best known as a member of the Celtic rock band O'Malley's March.
-
C.
Mike Lange
Mike Lange is a renowned American sportscaster best known as the longtime, colorful play-by-play announcer for the NHL’s Pittsburgh Penguins.
-
D.
Cam Gigandet
Cam Gigandet is an American actor known for his roles in films such as "Twilight," "Never Back Down," and various television series.
-
E.
David Hackney
David Hackney was an American guitarist and songwriter best known as a founding member of the pioneering Detroit proto-punk band Death.
- 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_69e245836014819091b91ed3074742a3 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f16162c2cc8190a506776ac52356d7 |
completed | April 29, 2026, 1:39 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b3d5c30a881908378d2b858c92e7e |
completed | May 18, 2026, 4:25 p.m. |
| NEDg | Description generation | batch_6a0b3f67df248190ab877b91cfec6772 |
completed | May 18, 2026, 4:33 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b3fe2ff80819099e665372b4e572b |
completed | May 18, 2026, 4:35 p.m. |
Created at: April 17, 2026, 2:49 p.m.