Triple
T21075289
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Drew |
E519216
|
entity |
| Predicate | hasFamilyName |
P18
|
FINISHED |
| Object | Drew |
—
|
NE NERFINISHED |
How this triple was built (2 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: Drew | Statement: [Thomas Drew, hasFamilyName, Drew]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Drew Context triple: [Thomas Drew, hasFamilyName, Drew]
-
A.
Drew
Drew is a Canadian professional ice hockey defenceman best known for his long career with the Los Angeles Kings in the NHL and multiple Stanley Cup and Olympic gold medal wins.
-
B.
Drew
chosen
Drew is a surname most prominently associated with American college basketball coach Scott Drew.
-
C.
Drew
Drew is a masculine given name commonly used in English-speaking countries, often as a short form of Andrew.
-
D.
Drew
Drew is a supporting character in the sitcom "Everybody Hates Chris," known as Chris's taller, more popular younger brother.
-
E.
Drew
Drew is a supporting character in the film "Meet Joe Black," serving as a corporate executive whose ambition and scheming contrast with the moral core of the story.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b506e59c8190849b71ed07929215 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e702d690dc8190839968b562e6b8bb |
completed | April 21, 2026, 4:53 a.m. |
Created at: April 16, 2026, 2:48 p.m.