Triple
T8512104
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thora Hird |
E201478
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | The Card |
E307745
|
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: The Card | Statement: [Thora Hird, notableWork, The Card]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Card Context triple: [Thora Hird, notableWork, The Card]
-
A.
The Card
chosen
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.
-
B.
Troika card
The Troika card is a reusable contactless smart card used for paying fares across Moscow’s public transportation system.
-
C.
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.
-
D.
Cardiac Cards
Cardiac Cards is a nickname for the former St. Louis Cardinals NFL team, referencing their dramatic, late-game comebacks and close finishes.
-
E.
Now cards
Now cards were context-aware information snippets in the Google Now service that proactively displayed personalized, timely updates such as weather, traffic, and reminders based on a user’s habits and location.
- 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_69ca8320e5748190ac2c585a0bba8193 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe60b0d4c8190812ddbc1c17389c8 |
completed | March 31, 2026, 3:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce4e4e64f481908ddf99570fe59332 |
completed | April 2, 2026, 11:09 a.m. |
Created at: March 30, 2026, 6:15 p.m.