Triple
T20878803
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Inventing Room |
E514089
|
entity |
| Predicate | notableInvention |
P4
|
FINISHED |
| Object |
Hair Toffee
Hair Toffee is a fictional candy from Roald Dahl’s "Charlie and the Chocolate Factory" that causes a person’s hair to grow rapidly and uncontrollably.
|
E1455053
|
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: Hair Toffee | Statement: [Inventing Room, notableInvention, Hair Toffee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hair Toffee Context triple: [Inventing Room, notableInvention, Hair Toffee]
-
A.
Toffee
Toffee is a calculating, immortal lizard-like monster and master strategist who serves as the primary villain opposing Star Butterfly in the animated series "Star vs. the Forces of Evil."
-
B.
Taffy
Taffy is a character featured in the film "On the Line."
-
C.
Moffat Toffee
Moffat Toffee is a traditional Scottish boiled sweet from the town of Moffat, noted for its hard exterior and tangy, chewy center.
-
D.
Toffen
Toffen is a small Swiss municipality in the canton of Bern, located in the Gürbetal valley near the city of Bern.
-
E.
Victoria Toffee
Victoria Toffee is a popular butter toffee confection from See’s Candies, known for its rich, crunchy texture and chocolate-and-nut coating.
- 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: Hair Toffee Triple: [Inventing Room, notableInvention, Hair Toffee]
Generated description
Hair Toffee is a fictional candy from Roald Dahl’s "Charlie and the Chocolate Factory" that causes a person’s hair to grow rapidly and uncontrollably.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Hair Toffee Target entity description: Hair Toffee is a fictional candy from Roald Dahl’s "Charlie and the Chocolate Factory" that causes a person’s hair to grow rapidly and uncontrollably.
-
A.
Toffee
Toffee is a calculating, immortal lizard-like monster and master strategist who serves as the primary villain opposing Star Butterfly in the animated series "Star vs. the Forces of Evil."
-
B.
Taffy
Taffy is a character featured in the film "On the Line."
-
C.
Moffat Toffee
Moffat Toffee is a traditional Scottish boiled sweet from the town of Moffat, noted for its hard exterior and tangy, chewy center.
-
D.
Toffen
Toffen is a small Swiss municipality in the canton of Bern, located in the Gürbetal valley near the city of Bern.
-
E.
Victoria Toffee
Victoria Toffee is a popular butter toffee confection from See’s Candies, known for its rich, crunchy texture and chocolate-and-nut coating.
- 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_69e0b4f733f081908a401c0b7beb0b9f |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c6775f108190a79cd5e8c31cecf6 |
completed | April 21, 2026, 12:36 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0913a242e08190be0a234ba5221a3a |
completed | May 17, 2026, 1:02 a.m. |
| NEDg | Description generation | batch_6a09146856cc819087dbfbe5f9b24bb1 |
completed | May 17, 2026, 1:05 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0915506ff48190a97f89092dac2ca2 |
completed | May 17, 2026, 1:09 a.m. |
Created at: April 16, 2026, 12:45 p.m.