Triple
T23362806
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eliza Walker |
E593229
|
entity |
| Predicate | coWorkerOf |
P398
|
FINISHED |
| Object | Hannah |
—
|
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: Hannah | Statement: [Eliza Walker, coWorkerOf, Hannah]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hannah Context triple: [Eliza Walker, coWorkerOf, Hannah]
-
A.
Hannah
Hannah is a compassionate Jewish laundress and the love interest of the Jewish Barber in Charlie Chaplin’s 1940 satirical film "The Great Dictator."
-
B.
Hannah
Hannah is a key survivor character in the British post-apocalyptic horror film "28 Days Later," known for her resilience and resourcefulness amid a rage virus outbreak in London.
-
C.
Hannah
Hannah is a feminine given name of Hebrew origin meaning "grace" or "favor," widely used in many English-speaking and international cultures.
-
D.
Hannah
Hannah is an alternative name or alias for the individual known as Anne.
-
E.
Hannah
"Hannah" is a 2017 Italian drama film directed by Andrea Pallaoro, featuring Charlotte Rampling in a critically acclaimed lead performance as a woman coping with isolation and personal crisis.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69e25d2593c88190bcdf4a716a94ccb2 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a0aa0ed88190b0198cbfd1bcc59b |
completed | April 29, 2026, 6:09 a.m. |
Created at: April 17, 2026, 5:30 p.m.