Triple
T4393448
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrew Card |
E99420
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Card |
E99420
|
NE FINISHED |
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: Card | Statement: [Andrew Card, familyName, Card]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Card Context triple: [Andrew Card, familyName, Card]
-
A.
Card
chosen
Card is a surname most notably borne by Andrew Card, a former White House Chief of Staff under U.S. President George W. Bush.
-
B.
CharlieCard
The CharlieCard is a reusable contactless smart card used to pay fares on Boston's MBTA public transit system.
-
C.
The Card
The Card is a comic novel by English writer Arnold Bennett that follows the ambitious rise of the charming and enterprising Edward Henry Machin in the fictional Five Towns.
-
D.
CharmCard
CharmCard is a contactless smart fare card used for paying transit fares across the Maryland Transit Administration’s bus, rail, and other public transportation services.
-
E.
Go-To Card
The Go-To Card is a reusable, contactless smart card used to pay fares on the Minneapolis–Saint Paul METRO transit system.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69b345506b408190b0e3dee616738a7d |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b352a8862481909dc67abf42be6928 |
completed | March 12, 2026, 11:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5e53385508190ac1261c44672070b |
completed | March 14, 2026, 10:46 p.m. |
Created at: March 12, 2026, 11:19 p.m.