Triple
T16875701
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Margaret Lockwood |
E421292
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Hungry Hill |
E1175996
|
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: Hungry Hill | Statement: [Margaret Lockwood, notableWork, Hungry Hill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hungry Hill Context triple: [Margaret Lockwood, notableWork, Hungry Hill]
-
A.
Hungry Hill
chosen
Hungry Hill is a prominent mountain on Ireland’s Beara Peninsula, known for its rugged terrain, scenic views, and popular hiking routes.
-
B.
The Angry Hills
The Angry Hills is a 1959 war drama film set in Nazi-occupied Greece, known for its tense espionage plot and starring Robert Mitchum and Gia Scala.
-
C.
Hanging Hills
Hanging Hills is a rugged traprock mountain ridge in central Connecticut known for its dramatic cliffs, scenic vistas, and popular hiking trails.
-
D.
The Walking Hills
The Walking Hills is a 1949 American Western film noir that blends a treasure-hunt plot with psychological drama, directed by John Sturges.
-
E.
Birdhill
Birdhill is a small rural village in County Tipperary, Ireland, known for its scenic setting near Lough Derg and the River Shannon.
- 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_69d889d470fc8190b4aec199636c0c56 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e3b7f646308190b5e277b5f51cd315 |
completed | April 18, 2026, 4:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00c2b4abd08190841c5bb0b0eaa177 |
completed | May 10, 2026, 5:39 p.m. |
Created at: April 10, 2026, 5:29 a.m.