Triple
T4832345
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Science Inc. |
E107972
|
entity |
| Predicate | portfolioBrand |
P12124
|
FINISHED |
| Object |
Wishbone
Wishbone is a mobile social networking app that lets users compare and vote between two options in quick, image-based polls.
|
E473170
|
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: Wishbone | Statement: [Science Inc., portfolioBrand, Wishbone]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wishbone Context triple: [Science Inc., portfolioBrand, Wishbone]
-
A.
The Fox
The Fox is a film featuring Sydney Chaplin, the son of legendary comedian and filmmaker Charlie Chaplin.
-
B.
The Fox
The Fox is a masked vigilante hero from early 20th-century California, best known for fighting injustice with cunning, swordplay, and a distinctive black costume and mask.
-
C.
The Fox
The Fox was the nickname of Johnny Torrio, an influential early 20th-century Italian-American mobster and mentor to Al Capone who helped shape organized crime in Chicago.
-
D.
Laika
Laika is an American stop-motion animation studio renowned for visually distinctive, critically acclaimed films such as Coraline, ParaNorman, and Kubo and the Two Strings.
-
E.
Laika
Laika was a Soviet space dog who became the first living creature to orbit Earth, marking a pivotal moment in the early Space Race.
- 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: Wishbone Triple: [Science Inc., portfolioBrand, Wishbone]
Generated description
Wishbone is a mobile social networking app that lets users compare and vote between two options in quick, image-based polls.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Wishbone Target entity description: Wishbone is a mobile social networking app that lets users compare and vote between two options in quick, image-based polls.
-
A.
The Fox
The Fox is a film featuring Sydney Chaplin, the son of legendary comedian and filmmaker Charlie Chaplin.
-
B.
The Fox
The Fox is a masked vigilante hero from early 20th-century California, best known for fighting injustice with cunning, swordplay, and a distinctive black costume and mask.
-
C.
The Fox
The Fox was the nickname of Johnny Torrio, an influential early 20th-century Italian-American mobster and mentor to Al Capone who helped shape organized crime in Chicago.
-
D.
Laika
Laika is an American stop-motion animation studio renowned for visually distinctive, critically acclaimed films such as Coraline, ParaNorman, and Kubo and the Two Strings.
-
E.
Laika
Laika was a Soviet space dog who became the first living creature to orbit Earth, marking a pivotal moment in the early Space Race.
- 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_69bd43fac8188190803f0327190621e4 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd7162427c81908a67a07545f698ae |
completed | March 20, 2026, 4:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be4dd4224c8190be7568bb611f81a3 |
completed | March 21, 2026, 7:50 a.m. |
| NEDg | Description generation | batch_69be51438c5881909f7456cdc3a60d98 |
completed | March 21, 2026, 8:05 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69be51a03f4c8190b04f0d3fe6486c24 |
completed | March 21, 2026, 8:06 a.m. |
Created at: March 20, 2026, 1:24 p.m.