Triple
T18721204
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cookie Gilchrist |
E457777
|
entity |
| Predicate | nickname |
P55
|
FINISHED |
| Object |
Cookie
Cookie is the nickname of Cookie Gilchrist, a prominent mid-20th-century professional football player known for his powerful running style in the CFL and AFL.
|
E1340271
|
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: Cookie | Statement: [Cookie Gilchrist, nickname, Cookie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cookie Context triple: [Cookie Gilchrist, nickname, Cookie]
-
A.
Cookie
Cookie is the nickname of Cookie Johnson, an American businesswoman, philanthropist, and the wife of NBA legend Magic Johnson.
-
B.
Cookie
"Cookie" is a song by American R&B singer R. Kelly from his album *Black Panties*, known for its sexually explicit lyrics and metaphorical wordplay.
-
C.
Cookie Fleck
Cookie Fleck is a neurotic, overly affectionate dog owner and former prom queen in the mockumentary film "Best in Show," known for her many ex-boyfriends and comic dynamic with her husband Gerry.
-
D.
Cookie Jar
"Cookie Jar" is a song featured on the album *On and On*, known for its catchy melody and reflective lyrics.
-
E.
HTTP cookies
HTTP cookies are small pieces of data stored by a web browser on behalf of a website to maintain stateful information such as sessions, preferences, and tracking across HTTP requests.
- 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: Cookie Triple: [Cookie Gilchrist, nickname, Cookie]
Generated description
Cookie is the nickname of Cookie Gilchrist, a prominent mid-20th-century professional football player known for his powerful running style in the CFL and AFL.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Cookie Target entity description: Cookie is the nickname of Cookie Gilchrist, a prominent mid-20th-century professional football player known for his powerful running style in the CFL and AFL.
-
A.
Cookie
Cookie is the nickname of Cookie Johnson, an American businesswoman, philanthropist, and the wife of NBA legend Magic Johnson.
-
B.
Cookie
"Cookie" is a song by American R&B singer R. Kelly from his album *Black Panties*, known for its sexually explicit lyrics and metaphorical wordplay.
-
C.
Cookie Fleck
Cookie Fleck is a neurotic, overly affectionate dog owner and former prom queen in the mockumentary film "Best in Show," known for her many ex-boyfriends and comic dynamic with her husband Gerry.
-
D.
Cookie Jar
"Cookie Jar" is a song featured on the album *On and On*, known for its catchy melody and reflective lyrics.
-
E.
HTTP cookies
HTTP cookies are small pieces of data stored by a web browser on behalf of a website to maintain stateful information such as sessions, preferences, and tracking across HTTP requests.
- 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_69d8d393ba9c8190a8b03b04ddbb0a09 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e56abadca08190ab1e699b7dcc0c4d |
completed | April 19, 2026, 11:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a053254700c8190a339be20720f5a33 |
completed | May 14, 2026, 2:24 a.m. |
| NEDg | Description generation | batch_6a0532de03488190abb9df6ea06f1150 |
completed | May 14, 2026, 2:26 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0533b186f48190be42122527d43b5b |
completed | May 14, 2026, 2:30 a.m. |
Created at: April 10, 2026, 11:50 a.m.