Triple
T13409215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Catherine Drinker Bowen |
E320044
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
Drinker
Drinker is a surname most notably associated with the American biographer Catherine Drinker Bowen and her prominent intellectual family.
|
E1039860
|
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: Drinker | Statement: [Catherine Drinker Bowen, familyName, Drinker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Drinker Context triple: [Catherine Drinker Bowen, familyName, Drinker]
-
A.
Bitterman
Bitterman is a prominent playable marine character from the Quake series, best known as the main protagonist of Quake II.
-
B.
Tom the barman
Tom the barman is the hunchbacked, toothless innkeeper of the Leaky Cauldron pub in the Harry Potter series, known for serving wizards and witches at the gateway between Muggle London and Diagon Alley.
-
C.
Keggy the Keg
Keggy the Keg is an unofficial, student-created anthropomorphic beer keg mascot associated with Dartmouth College’s athletic culture and campus traditions.
-
D.
Beery
Beery is a surname most notably associated with the American acting family that includes character actor Noah Beery and his relatives.
-
E.
Braxus
Braxus is the primary demonic antagonist in the fantasy film "Beastmaster III: The Eye of Braxus."
- 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: Drinker Triple: [Catherine Drinker Bowen, familyName, Drinker]
Generated description
Drinker is a surname most notably associated with the American biographer Catherine Drinker Bowen and her prominent intellectual family.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Drinker Target entity description: Drinker is a surname most notably associated with the American biographer Catherine Drinker Bowen and her prominent intellectual family.
-
A.
Bitterman
Bitterman is a prominent playable marine character from the Quake series, best known as the main protagonist of Quake II.
-
B.
Tom the barman
Tom the barman is the hunchbacked, toothless innkeeper of the Leaky Cauldron pub in the Harry Potter series, known for serving wizards and witches at the gateway between Muggle London and Diagon Alley.
-
C.
Keggy the Keg
Keggy the Keg is an unofficial, student-created anthropomorphic beer keg mascot associated with Dartmouth College’s athletic culture and campus traditions.
-
D.
Beery
Beery is a surname most notably associated with the American acting family that includes character actor Noah Beery and his relatives.
-
E.
Braxus
Braxus is the primary demonic antagonist in the fantasy film "Beastmaster III: The Eye of Braxus."
- 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_69d806b943cc8190b6af624d385d7e12 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbae4d2c5481908facfaaa1501e344 |
completed | April 12, 2026, 2:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7307ccff08190aa4037aa5a48f7d0 |
completed | May 3, 2026, 11:24 a.m. |
| NEDg | Description generation | batch_69f7313c6bcc8190a848cf8945a0ae2a |
completed | May 3, 2026, 11:27 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f736f2f6a081908d532dba6f34ed97 |
completed | May 3, 2026, 11:52 a.m. |
Created at: April 9, 2026, 9:35 p.m.