Triple
T2624471
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taronga Zoo |
E59083
|
entity |
| Predicate | hasExhibit |
P35
|
FINISHED |
| Object |
Tiger Trek
Tiger Trek is an immersive Sumatran tiger exhibit at Taronga Zoo that recreates an Indonesian village environment to highlight tiger conservation.
|
E282926
|
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: Tiger Trek | Statement: [Taronga Zoo, hasExhibit, Tiger Trek]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tiger Trek Context triple: [Taronga Zoo, hasExhibit, Tiger Trek]
-
A.
Panda Trek
Panda Trek is a themed exhibit at the San Diego Zoo that immerses visitors in a Chinese forest environment featuring giant pandas and other Asian wildlife.
-
B.
Save the Tiger
Save the Tiger is a 1973 American drama film starring Jack Lemmon as a troubled businessman facing a midlife and moral crisis.
-
C.
Roaring Tiger
Roaring Tiger is the fierce tiger mascot representing Colorado College’s athletic teams and school spirit.
-
D.
The Tiger
The Tiger is the costumed feline mascot that represents Princeton University's athletic teams, particularly its football program.
-
E.
Elephant Lands
Elephant Lands is a large, naturalistic elephant habitat and exhibit at the Oregon Zoo designed to support the physical and behavioral needs of Asian elephants.
- 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: Tiger Trek Triple: [Taronga Zoo, hasExhibit, Tiger Trek]
Generated description
Tiger Trek is an immersive Sumatran tiger exhibit at Taronga Zoo that recreates an Indonesian village environment to highlight tiger conservation.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tiger Trek Target entity description: Tiger Trek is an immersive Sumatran tiger exhibit at Taronga Zoo that recreates an Indonesian village environment to highlight tiger conservation.
-
A.
Panda Trek
Panda Trek is a themed exhibit at the San Diego Zoo that immerses visitors in a Chinese forest environment featuring giant pandas and other Asian wildlife.
-
B.
Save the Tiger
Save the Tiger is a 1973 American drama film starring Jack Lemmon as a troubled businessman facing a midlife and moral crisis.
-
C.
Roaring Tiger
Roaring Tiger is the fierce tiger mascot representing Colorado College’s athletic teams and school spirit.
-
D.
The Tiger
The Tiger is the costumed feline mascot that represents Princeton University's athletic teams, particularly its football program.
-
E.
Elephant Lands
Elephant Lands is a large, naturalistic elephant habitat and exhibit at the Oregon Zoo designed to support the physical and behavioral needs of Asian elephants.
- 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_69ab4ac558388190962492cd2e1b0ce6 |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abd8b061a08190b7a8459851abaae2 |
completed | March 7, 2026, 7:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af909b7d9881908930a98d004998fb |
completed | March 10, 2026, 3:31 a.m. |
| NEDg | Description generation | batch_69af913e20848190a25c90617df6ea6f |
completed | March 10, 2026, 3:34 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69af91e0ef408190b1ab9cb9f8bbdaca |
completed | March 10, 2026, 3:37 a.m. |
Created at: March 6, 2026, 9:50 p.m.