Triple
T3965387
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flesh and Stone |
E92204
|
entity |
| Predicate | featuresCharacter |
P626
|
FINISHED |
| Object |
Angel Bob
Angel Bob is a disembodied, time-manipulating Weeping Angel who communicates through a victim’s voice in the Doctor Who episode "Flesh and Stone."
|
E402739
|
NE FINISHED |
How this triple was built (4 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: Angel Bob | Statement: [Flesh and Stone, featuresCharacter, Angel Bob]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Angel Bob Context triple: [Flesh and Stone, featuresCharacter, Angel Bob]
-
A.
Handsome Bob
Handsome Bob is a stylish, soft-spoken gangster and member of One Two’s crew in Guy Ritchie’s crime film "RocknRolla."
-
B.
Iron Felix
Iron Felix is the nickname of Felix Dzerzhinsky, the Soviet revolutionary who founded and led the Cheka, the Bolshevik secret police.
-
C.
Wilbert
Wilbert is the given first name of American character actor Bill Cobbs, known for his numerous supporting roles in film and television.
-
D.
Garth
Garth is a fictional character from the American prime-time television soap opera "Falcon Crest."
-
E.
Garth
Garth is a novel by American writer Julian Hawthorne, known as one of his more prominent works of fiction in the late 19th century.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Angel Bob Triple: [Flesh and Stone, featuresCharacter, Angel Bob]
Generated description
Angel Bob is a disembodied, time-manipulating Weeping Angel who communicates through a victim’s voice in the Doctor Who episode "Flesh and Stone."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Angel Bob Target entity description: Angel Bob is a disembodied, time-manipulating Weeping Angel who communicates through a victim’s voice in the Doctor Who episode "Flesh and Stone."
-
A.
Handsome Bob
Handsome Bob is a stylish, soft-spoken gangster and member of One Two’s crew in Guy Ritchie’s crime film "RocknRolla."
-
B.
Iron Felix
Iron Felix is the nickname of Felix Dzerzhinsky, the Soviet revolutionary who founded and led the Cheka, the Bolshevik secret police.
-
C.
Wilbert
Wilbert is the given first name of American character actor Bill Cobbs, known for his numerous supporting roles in film and television.
-
D.
Garth
Garth is a fictional character from the American prime-time television soap opera "Falcon Crest."
-
E.
Garth
Garth is a novel by American writer Julian Hawthorne, known as one of his more prominent works of fiction in the late 19th century.
- F. None of above. chosen
Provenance (5 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_69aed96624188190ac8c45bb57ab72b5 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef97520588190922e56201fc3ca52 |
completed | March 9, 2026, 4:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b533be4a688190a7d011ae2858e6ed |
completed | March 14, 2026, 10:09 a.m. |
| NEDg | Description generation | batch_69b537cc86e88190bae10e740d8c3ec7 |
completed | March 14, 2026, 10:26 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b538595d2481908812ab03cdb94659 |
completed | March 14, 2026, 10:28 a.m. |
Created at: March 9, 2026, 3:31 p.m.