Triple

T36281169
Position Surface form Disambiguated ID Type / Status
Subject Hannibal Chew E892944 entity
Predicate eyeTypeProduced P39138 FINISHED
Object Replicant eyes
Replicant eyes are the artificial, bioengineered eyes created for synthetic humans in the Blade Runner universe, crucial to their identity and often used as a visual motif to distinguish them from real humans.
 E2176794 NE FINISHED

How this triple was built (3 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: Replicant eyes | Statement: [Hannibal Chew, eyeTypeProduced, Replicant eyes]
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: Replicant eyes
Triple: [Hannibal Chew, eyeTypeProduced, Replicant eyes]
Generated description
Replicant eyes are the artificial, bioengineered eyes created for synthetic humans in the Blade Runner universe, crucial to their identity and often used as a visual motif to distinguish them from real humans.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: eyeTypeProduced
Context triple: [Hannibal Chew, eyeTypeProduced, Replicant eyes]
  • A. eyeType chosen
    Indicates the specific kind or category of eyes an entity has, such as their form, structure, or visual style.
  • B. oculusDiameter
    Indicates the diameter measurement of an oculus (a circular opening), relating the opening to the size of its circular span.
  • C. eyeCharacteristic
    Indicates a relationship where an entity possesses a specific attribute, feature, or quality of its eyes.
  • D. eyeCount
    Indicates the number of eyes an entity has.
  • E. hasEyes
    Indicates that an entity possesses eyes as physical features.
  • F. None of above.

Provenance (6 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_69f76e4955c08190b8cfddca34fc0242 completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_69f7ba6d06f48190a71b5a2f19e2232f completed May 3, 2026, 9:13 p.m.
NED1 Entity disambiguation (via context triple) batch_6a396e196e5c8190935a98180bdf1fe0 completed June 22, 2026, 5:17 p.m.
NEDg Description generation batch_6a396fe4e80c81909bb4e20087f46214 completed June 22, 2026, 5:24 p.m.
NED2 Entity disambiguation (via description) batch_6a3972b9e1208190896dd528ca98bbbc completed June 22, 2026, 5:36 p.m.
PD Predicate disambiguation batch_69f7b9a4aad48190a62e41c5e39339d9 completed May 3, 2026, 9:09 p.m.
Created at: May 3, 2026, 4:09 p.m.