Triple

T5215523
Position Surface form Disambiguated ID Type / Status
Subject Joan Harrison E117742 entity
Predicate notableWork P4 FINISHED
Object Phantom Lady
Phantom Lady is a 1944 American film noir crime drama, based on Cornell Woolrich’s novel, about a man trying to clear his name of murder with the help of his loyal secretary.
E503929 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: Phantom Lady | Statement: [Joan Harrison, notableWork, Phantom Lady]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Phantom Lady
Context triple: [Joan Harrison, notableWork, Phantom Lady]
  • A. The Phantom
    The Phantom is the main terrorist antagonist in the 2008 Adam Sandler comedy film "You Don’t Mess with the Zohan."
  • B. The Lady Killer
    The Lady Killer is CeeLo Green’s critically acclaimed 2010 soul and R&B album best known for the hit single "Forget You."
  • C. Lady of Terror
    Lady of Terror is an epithet of the Egyptian goddess Sekhmet, highlighting her fearsome power as a lioness deity of war, destruction, and divine retribution.
  • D. Phantom
    Phantom is a hostile flying undead mob in Minecraft that swoops down from the night sky to attack players who haven’t slept for several days.
  • E. Phantom
    Phantom is a music production alias associated with Ye (formerly Kanye West), under which he has created and produced tracks.
  • 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: Phantom Lady
Triple: [Joan Harrison, notableWork, Phantom Lady]
Generated description
Phantom Lady is a 1944 American film noir crime drama, based on Cornell Woolrich’s novel, about a man trying to clear his name of murder with the help of his loyal secretary.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Phantom Lady
Target entity description: Phantom Lady is a 1944 American film noir crime drama, based on Cornell Woolrich’s novel, about a man trying to clear his name of murder with the help of his loyal secretary.
  • A. The Phantom
    The Phantom is the main terrorist antagonist in the 2008 Adam Sandler comedy film "You Don’t Mess with the Zohan."
  • B. The Lady Killer
    The Lady Killer is CeeLo Green’s critically acclaimed 2010 soul and R&B album best known for the hit single "Forget You."
  • C. Lady of Terror
    Lady of Terror is an epithet of the Egyptian goddess Sekhmet, highlighting her fearsome power as a lioness deity of war, destruction, and divine retribution.
  • D. Phantom
    Phantom is a hostile flying undead mob in Minecraft that swoops down from the night sky to attack players who haven’t slept for several days.
  • E. Phantom
    Phantom is a music production alias associated with Ye (formerly Kanye West), under which he has created and produced tracks.
  • 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_69bd4464ba3c8190bc16b2ebbe42ddb0 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7a928dfc8190971a9e28d5c10446 completed March 20, 2026, 4:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69beefe788f88190a2ac0673daafaab2 completed March 21, 2026, 7:22 p.m.
NEDg Description generation batch_69bef28b79588190a2f38f208c9e93de completed March 21, 2026, 7:33 p.m.
NED2 Entity disambiguation (via description) batch_69bef2e568ec8190b14d686508850b7c completed March 21, 2026, 7:35 p.m.
Created at: March 20, 2026, 1:48 p.m.