Triple
T10295746
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Jane Croft |
E241481
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Croft |
E830905
|
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: Croft | Statement: [Mary Jane Croft, familyName, Croft]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Croft Context triple: [Mary Jane Croft, familyName, Croft]
-
A.
Croft
Croft is a village and civil parish in the borough of Warrington, Cheshire, England, known for its rural character and annual Croft Carnival.
-
B.
Croft
chosen
Croft is the surname of Lara Croft, the iconic archaeologist-adventurer protagonist of the Tomb Raider video game franchise.
-
C.
Croft Manor
Croft Manor is the grand ancestral estate and primary home of fictional archaeologist-adventurer Lara Croft in the Tomb Raider video game franchise.
-
D.
The Croft
The Croft is a residential neighborhood located near Palacefields in the town of Runcorn, Cheshire, England.
-
E.
Lofthouse
Lofthouse is a small rural village in North Yorkshire, England, known for its scenic setting in the Nidderdale valley and access to surrounding moorland and reservoirs.
- 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_69d381aaafc08190af475ef58dc16aba |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d2ea9b3c8190b11518b259d5825c |
completed | April 7, 2026, 9:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d71d23f49081909aea149c6b219354 |
completed | April 9, 2026, 3:29 a.m. |
Created at: April 6, 2026, 11:43 a.m.